> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.umnai.com/ui-guides/explanations/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.umnai.com/_mcp/server.

# Explanation Lab

## Docs

- [Explanation views](https://docs.umnai.com/ui-guides/explanations/overview.md): Choose a view for predictions, learned rules or generated interpretations.
- [Local explanations](https://docs.umnai.com/ui-guides/explanations/local-explanations.md): Query a record and inspect its prediction and explanation.
- [Feature and module attributions](https://docs.umnai.com/ui-guides/explanations/attributions.md): Inspect how features and modules contribute to a prediction.
- [Model structure and decision rules](https://docs.umnai.com/ui-guides/explanations/decision-rules.md): Browse modules, partitions, conditions and rule expressions.
- [Module dependencies](https://docs.umnai.com/ui-guides/explanations/module-dependencies.md): Inspect dependency plots and use the Module Explorer.
- [Dependency graph](https://docs.umnai.com/ui-guides/explanations/dependency-graph.md): Trace the displayed computation from inputs through modules to output.
- [XNN-assisted LLM explanations](https://docs.umnai.com/ui-guides/explanations/llm-explanations.md): Generate and review an interpretation of the built-in sample data.
- [Symbolic explanations](https://docs.umnai.com/ui-guides/explanations/symbolic-explanations.md): Generate and review a written interpretation of a module’s rules.
- [Use explanations](https://docs.umnai.com/ui-guides/explanations/using-explanations.md): Retain the context needed to interpret and reuse explanations.