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

    Neuronpedia

    INDEX
    Explanations

    white noise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ુ
    1.30
    나
    1.12
    はありません
    1.10
     totale
    1.09
    皆さん
    1.06
    ל
    1.05
    已知
    1.04
    urile
    1.03
    もない
    1.03
    쌔
    1.02
    POSITIVE LOGITS
     деву
    1.16
     человека
    1.11
    larından
    1.09
    getItems
    1.09
     scripture
    1.08
    ссмо
    1.05
    airobi
    1.02
     intently
    1.02
    തിയ
    1.02
    ut
    1.01
    Act Density 0.001%

    No Known Activations