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

    Neuronpedia

    INDEX
    Explanations

    usd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bolognese
    0.82
     gonorrhea
    0.82
     outubro
    0.78
     hickory
    0.77
    㩴
    0.76
    称为
    0.76
     Parmesan
    0.76
    otle
    0.75
    ⭑
    0.75
     CallbackContext
    0.74
    POSITIVE LOGITS
    ح
    0.93
    در
    0.87
    ت
    0.82
    larni
    0.77
    lerdir
    0.75
    پ
    0.73
    ч
    0.72
    ية
    0.71
    ای
    0.71
    رد
    0.71
    Act Density 0.001%

    No Known Activations