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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anonymous
    -0.07
    .bias
    -0.07
    _POLICY
    -0.07
    靸
    -0.07
    暂缓
    -0.07
    Dire
    -0.07
    精准
    -0.07
    電子信箱
    -0.07
    共计
    -0.07
     severely
    -0.07
    POSITIVE LOGITS
    女兒
    0.07
     uomini
    0.07
    .broadcast
    0.07
     furn
    0.07
    izen
    0.07
    flen
    0.07
    ysts
    0.07
    rat
    0.06
     uterus
    0.06
     Ấn
    0.06
    Act Density 0.004%

    No Known Activations