Antigravity Agent
32 lines
1.1 KiB
Markdown
32 lines
1.1 KiB
Markdown
---
|
|
id: wiki-2026-0508-model-interpretability-tools
|
|
title: Model Interpretability Tools
|
|
category: 10_Wiki/Topics
|
|
status: duplicate
|
|
canonical_id: "[[Explainable-AI-XAI]]"
|
|
aliases: [Model Interpretability, Interpretability Tools, ML Explainability Tools]
|
|
duplicate_of: "[[Explainable-AI-XAI]]"
|
|
source_trust_level: A
|
|
confidence_score: 0.88
|
|
verification_status: redirected
|
|
tags: [redirect, xai, interpretability, ml-tooling]
|
|
raw_sources: []
|
|
last_reinforced: 2026-05-10
|
|
github_commit: pending
|
|
tech_stack: { language: python, framework: shap-lime-captum }
|
|
---
|
|
|
|
## Redirect
|
|
|
|
This page redirects to the canonical entry **[[Explainable-AI-XAI]]**.
|
|
|
|
Model interpretability tools (SHAP, LIME, Captum, InterpretML, transformer-lens, TCAV 등)는 XAI 분야의 구현 도구이며, 개념·분류·평가 기준은 canonical 문서에서 통합 관리한다.
|
|
|
|
## 🔗 Graph
|
|
- 부모(canonical): [[Explainable-AI-XAI]]
|
|
- 관련: [[SHAP]], [[LIME]], [[Captum]], [[Mechanistic-Interpretability]], [[Feature-Attribution]]
|
|
|
|
## 🕓 Changelog
|
|
- Phase 1 (2026-05-08): 초기 생성.
|
|
- Manual cleanup (2026-05-10): REDIRECT 확정, canonical은 [[Explainable-AI-XAI]].
|