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

    Neuronpedia

    INDEX
    Explanations

    file processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [t
    -0.07
    _hdl
    -0.07
     mời
    -0.07
    mp
    -0.07
     Trusted
    -0.07
    מסלול
    -0.07
    RAR
    -0.07
     blame
    -0.07
    🍪
    -0.07
    Eventually
    -0.07
    POSITIVE LOGITS
    การแสดง
    0.07
    我个人
    0.06
    乳业
    0.06
    切
    0.06
    童话
    0.06
    以色列
    0.06
    ગ
    0.06
     GCBO
    0.06
    擐
    0.06
    人民政府
    0.06
    Act Density 0.122%

    No Known Activations