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

    Neuronpedia

    INDEX
    Explanations

    taking initiative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stal
    -0.07
    {}_
    -0.07
     Computer
    -0.06
     {}
↵
    -0.06
     Typically
    -0.06
    (directory
    -0.06
     Zhao
    -0.06
    Lambda
    -0.06
     '{$
    -0.06
     Thema
    -0.06
    POSITIVE LOGITS
     carr
    0.06
     innate
    0.06
    ‡
    0.06
    fixed
    0.06
    CC
    0.06
    /fw
    0.06
     LatLng
    0.06
    _fm
    0.06
     determinant
    0.06
    ětí
    0.06
    Act Density 0.012%

    No Known Activations