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

    Neuronpedia

    INDEX
    Explanations

    Spanish translations and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.59
    a
    0.53
    ه
    0.52
    פ
    0.52
     受
    0.48
    精灵
    0.48
    ב
    0.48
     RPC
    0.48
     निश्च
    0.47
     Botox
    0.47
    POSITIVE LOGITS
    ía
    0.48
    án
    0.48
    assador
    0.47
    тери
    0.45
     Олександр
    0.44
    лам
    0.44
    uter
    0.43
    itt
    0.43
    utter
    0.43
    anches
    0.41
    Act Density 0.001%

    No Known Activations