Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    款车型
    -0.07
    ⽺
    -0.07
    سلح
    -0.07
    뽕
    -0.07
    plätze
    -0.07
    :type
    -0.07
    搜狐首页
    -0.07
    ayette
    -0.07
     المسلمين
    -0.07
    >About
    -0.07
    POSITIVE LOGITS
     Figure
    0.07
    athy
    0.07
     м
    0.07
    _EM
    0.07
     controllers
    0.06
    —all
    0.06
    𝙤
    0.06
     Isaiah
    0.06
    下
    0.06
    Flo
    0.06
    Act Density 0.014%

    No Known Activations