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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.86
     Paglinawan
    -0.82
    хьтан
    -0.82
     الرياضيه
    -0.81
     anaemia
    -0.81
    anyahu
    -0.79
     betweenstory
    -0.79
     оригіналу
    -0.78
    TypedDataSet
    -0.77
     photolibrary
    -0.77
    POSITIVE LOGITS
    .
    0.97
    0
    0.88
    -
    0.83
    ,
    0.78
    th
    0.77
    rd
    0.76
    /
    0.71
     or
    0.68
    x
    0.67
    D
    0.66
    Act Density 1.227%

    No Known Activations