> For the complete documentation index, see [llms.txt](https://docs.neurolabai.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.neurolabai.io/start-using-neurolab/knowledge-graph-explorer.md).
# The Evidence Topology Explorer
The Evidence Topology Explorer visualizes the evidence and context attached to the current report. It is not a browser for the complete Neurolab knowledge graph and not a literal trace of the GNN's message passing.
## Choose a view
### 2D evidence map
Use one of three layouts:
* **Evidence Orbit** groups material around the report’s focal entities.
* **Type Columns** separates nodes by type for comparison.
* **Evidence Hierarchy** emphasizes the path from report claim to support and source.
### 3D Evidence Constellation
The 3D view is an interactive representation of abstract graph topology. Position, distance, and direction do not represent anatomy, physical scale, biological propagation, or time. If WebGL is unavailable, return to a 2D layout.
## Find and inspect
The find and inspect feature enables searching the inference report's evidence topology by entity label, type, or stable identifier. Filters can narrow entity types and evidence states; server-provided filters can further bound the returned artifact. Selecting an item opens details for a node, edge, evidence record, source, or path.
Read these fields together:
* evidence state and support scope;
* relation direction and conservative sign;
* relation-specific weight, if present;
* source and citation metadata;
* coverage and truncation notices; and
* stable node, edge, evidence, and path identifiers.
Facts and evidence can be updated independently of the predictive model. Check the model release and the facts-and-evidence release before comparing graph artifacts produced at different times.
Path highlighting shows a path represented in the report-local artifact. Inactive reference paths are opt-in context and do not mean that the compound activated or traversed them.
## Continue the investigation
From a selection you can attach the graph or selected items to chat, ask about the selection, open relevant brain context, or locate the source field in Raw Report. These actions preserve a shared report context; they do not create a new prediction.
## Export responsibly
* **Graph JSON** preserves the machine-readable artifact and stable identifiers.
* **SVG** is useful for scalable 2D figures.
* **PNG** is useful for fixed visual snapshots.
Keep coverage, filters, truncation, release identity, and caveats with any export. A visually central node is not necessarily causal, highly confident, or important to the GNN.
***
Next: [Brain Explorer](/start-using-neurolab/brain-explorer.md)
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.neurolabai.io/start-using-neurolab/knowledge-graph-explorer.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
