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

    Neuronpedia

    INDEX
    Explanations

    background information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ě
    0.81
     вас
    0.80
    كت
    0.75
    ك
    0.73
    يب
    0.72
    ö
    0.72
     as
    0.70
     તમારા
    0.68
     ještě
    0.67
    ů
    0.67
    POSITIVE LOGITS
    i
    1.33
     Background
    1.30
    m
    1.27
    background
    1.21
    Background
    1.18
    a
    1.13
     background
    1.09
    ে
    1.09
     backgrounds
    1.02
    n
    0.99
    Act Density 0.054%

    No Known Activations