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

    Neuronpedia

    INDEX
    Explanations

    percentage calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.86
     at
    0.86
    ك
    0.84
     an
    0.83
    یت
    0.82
     the
    0.80
    ac
    0.77
    iel
    0.76
    an
    0.75
    ка
    0.75
    POSITIVE LOGITS
    ’
    1.18
    Percentage
    0.85
    ти
    0.78
     porcent
    0.77
     (\%)
    0.75
     percentages
    0.74
    Percentages
    0.73
    ’)
    0.71
     percentage
    0.70
     Percentage
    0.70
    Act Density 0.008%

    No Known Activations