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

    Neuronpedia

    INDEX
    Explanations

    percentage symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.62
    ichte
    0.61
    $
    0.61
    The
    0.59
    дко
    0.56
    ite
    0.56
    ла
    0.56
    1
    0.55
    ೀಯ
    0.52
    す楽
    0.52
    POSITIVE LOGITS
     मगर
    0.59
     وفي
    0.59
     inaccessible
    0.57
     ومع
    0.56
     Energies
    0.56
     निसाब
    0.55
     exacerbated
    0.55
    ഷേധ
    0.55
    但在
    0.54
    是非常
    0.54
    Act Density 0.217%

    No Known Activations