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

    Neuronpedia

    INDEX
    Explanations

    cataloging and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wrongly
    0.45
     lekin
    0.44
     hilfre
    0.43
    是要
    0.41
     ngunit
    0.41
    的重要
    0.40
     invariable
    0.40
     ولكن
    0.40
     disob
    0.40
     而且
    0.39
    POSITIVE LOGITS
    薩
    0.47
    Compras
    0.42
    Bruno
    0.42
    क
    0.42
    Px
    0.41
    ะ
    0.41
    ९
    0.41
    ிலோ
    0.41
    cribable
    0.41
    Buck
    0.41
    Act Density 0.013%

    No Known Activations