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

    Neuronpedia

    INDEX
    Explanations

    assignment operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {(
    0.74
     Besides
    0.70
     endere
    0.68
     pasted
    0.68
    ombies
    0.67
    outine
    0.67
     Cur
    0.67
    actif
    0.67
    inko
    0.67
    urrences
    0.66
    POSITIVE LOGITS
     사회
    0.72
     /=
    0.70
     سیاسی
    0.68
     =
    0.68
    亚洲
    0.63
     시대
    0.62
     ecological
    0.62
     изображения
    0.61
     헤
    0.61
    ^{*}=
    0.61
    Act Density 0.160%

    No Known Activations