neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻譯準備中
以版本庫為基礎的設定,適用於 Claude Code 與 Codex CLI,包含 Kimi、MiniMax、Z.ai / GLM,以及共享的外掛、技能與掛鉤。
AI 翻譯
Repository-backed settings for Claude Code and Codex CLI, including Kimi, MiniMax, Z.ai / GLM, plus shared plugins, skills and hooks.
開發工具Python · MDXGitHub @fcakyon上線中營運者未確認
試用過了嗎? 點一下就好,不需要登入。
經過實戰驗證的 Claude Code、OpenAI Codex、Cursor 設定、外掛、掛鉤與代理人,支援 Kimi、MiniMax 與 GLM API。
AI 翻譯
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Battle-tested Claude Code, Claude Desktop, OpenAI Codex, and Cursor setup with skills, commands, hooks, subagents, and MCP servers, plus Kimi, MiniMax, and GLM API support.
"They make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs. They really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves." -- Andrej Karpathy檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
Battle-tested Claude Code, Claude Desktop, OpenAI Codex, and Cursor setup with skills, commands, hooks, subagents, and MCP servers, plus Kimi, MiniMax, and GLM API support.
"They make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs. They really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves." -- Andrej Karpathy檢視完整 README ↗