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

    Neuronpedia

    INDEX
    Explanations

    website homepage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    1.09
    I
    0.82
    ل
    0.70
    A
    0.65
    T
    0.63
    MAR
    0.61
    {
    0.60
     on
    0.60
    。
    0.59
     as
    0.59
    POSITIVE LOGITS
    ви
    0.64
     بنی
    0.62
     Bernadette
    0.61
    ﻦ
    0.60
    owymi
    0.60
     다섯
    0.59
     QLabel
    0.58
    ты
    0.57
     homepage
    0.57
     και
    0.56
    Act Density 0.003%

    No Known Activations