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

    Neuronpedia

    INDEX
    Explanations

    I statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    те
    3.02
    ف
    2.75
    ن
    2.75
    f
    2.59
     intrig
    2.44
    osť
    2.41
    ك
    2.38
    s
    2.32
     frutto
    2.29
    ع
    2.25
    POSITIVE LOGITS
    வ்வளவு
    2.43
     nostri
    2.41
     Sparks
    2.23
     samband
    2.23
     constitué
    2.23
     управления
    2.22
    ያንዳ
    2.15
     profond
    2.04
    statusCode
    2.04
    roquois
    2.03
    Act Density 0.000%

    No Known Activations