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

    Neuronpedia

    INDEX
    Explanations

    exclamations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     являются
    0.63
    <unused9>
    0.62
     стиль
    0.62
     имена
    0.62
     имя
    0.61
     sétimo
    0.61
    '،
    0.61
    둥
    0.61
    ரசுக்
    0.60
     видео
    0.60
    POSITIVE LOGITS
    r
    0.75
    iss
    0.73
    :
    0.71
     V
    0.70
    il
    0.70
    d
    0.67
    ts
    0.66
     (
    0.66
     W
    0.66
    t
    0.65
    Act Density 0.000%

    No Known Activations