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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     not
    0.77
    ,
    0.71
     top
    0.66
     no
    0.66
     only
    0.63
     other
    0.62
     before
    0.61
     still
    0.60
     completely
    0.60
     sam
    0.59
    POSITIVE LOGITS
    órmula
    0.82
    ഽ
    0.73
    fungsi
    0.72
    parseFloat
    0.71
    ጠቀም
    0.70
    Jumlah
    0.70
    㪇
    0.70
    jumlah
    0.70
    Produtos
    0.69
    Sqrt
    0.68
    Act Density 0.780%

    No Known Activations