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
尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證🔒 Permix is a lightweight, framework-agnostic, type-safe permissions management library for TypeScript applications on the client and server sides.
翻譯準備中
取自儲存庫 README
正在載入完整 README。
檢視完整 README ↗Permix is a lightweight, framework-agnostic, type-safe permissions management library for JavaScript applications on the client and server sides.
You can find the documentation here.
To quick start you only need to write the following code:
import { createPermix } from 'permix'
const permix = createPermix<{
post: ['read']
}>()
permix.setup({
post: {
read: true,
},
})
permix.check('post.read') // true
Permix has other powerful features, so here's check out the docs or the examples directory.
Your agents know every permission in place: the whole permission model lives in one typed createPermix<...> schema, and any permission an agent invents, misspells, or forgets is a TypeScript error.
npx skills add letstri/permix, or copy them from node_modules/permix/skills/ so they match your installed version.llms.txt, llms-full.txt, and any docs page as Markdown by appending .md to its URL.AGENTS.md conventions, and gating in-app AI tools: AI Agents guide.MIT License - see the LICENSE file for details