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

    Neuronpedia

    INDEX
    Explanations

    code and data formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _soft
    -0.06
    (pow
    -0.06
     уточ
    -0.06
    不到
    -0.06
     prosecute
    -0.06
    _atom
    -0.06
     editors
    -0.06
    .Highlight
    -0.06
    для
    -0.06
    ulur
    -0.06
    POSITIVE LOGITS
     المف
    0.06
     sincerely
    0.06
    _pub
    0.06
    ائز
    0.06
     Hive
    0.06
     dei
    0.06
     repe
    0.06
     Fell
    0.06
     عام
    0.06
    _oauth
    0.06
    Act Density 0.365%

    No Known Activations