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

    Neuronpedia

    INDEX
    Explanations

    regular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    are
    -0.07
    *T
    -0.06
     fairy
    -0.06
    bot
    -0.06
     bright
    -0.06
     fant
    -0.06
     seeds
    -0.06
    而
    -0.06
     lesson
    -0.06
     demonstration
    -0.06
    POSITIVE LOGITS
     سرم
    0.07
     atIndex
    0.06
    ologické
    0.06
    ？」
    0.06
     زبان
    0.06
    :String
    0.06
    aştır
    0.06
     bigint
    0.06
    Series
    0.06
     쓰
    0.06
    Act Density 0.016%

    No Known Activations