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

    Neuronpedia

    INDEX
    Explanations

    vulnerability and researchgate publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    作为
    0.43
    Parsed
    0.41
    PluginResult
    0.41
     rejected
    0.41
     sigma
    0.40
     decomposed
    0.40
     denominado
    0.38
     compromised
    0.38
     marginalised
    0.38
     resisted
    0.38
    POSITIVE LOGITS
     تمام
    0.43
    kec
    0.42
     عرضه
    0.39
    予算
    0.39
     एक्टर
    0.38
     কীটপত
    0.38
     कार्यक्रम
    0.38
     μόνο
    0.37
     आणखी
    0.37
     toàn
    0.37
    Act Density 0.000%

    No Known Activations