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

    Neuronpedia

    INDEX
    Explanations

    locations or specific places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MENT
    0.82
     Dumb
    0.80
     depreci
    0.79
     себя
    0.77
    ment
    0.76
     của
    0.76
     Heter
    0.75
    ात्
    0.75
    HEIM
    0.74
    ্লিকেশন
    0.73
    POSITIVE LOGITS
    ا
    0.75
    ის
    0.69
    ﺍ
    0.68
    بي
    0.66
    会
    0.66
    सी
    0.64
     certains
    0.64
     protože
    0.63
     رائ
    0.62
    라
    0.62
    Act Density 0.000%

    No Known Activations