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

    Neuronpedia

    INDEX
    Explanations

    API keys and related usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ness
    0.48
     system
    0.46
     vitro
    0.45
     (
    0.42
    th
    0.42
     realm
    0.42
    ity
    0.42
    most
    0.42
    \\
    0.42
     empire
    0.41
    POSITIVE LOGITS
    İM
    0.49
    परिवार
    0.47
     年度
    0.46
    内外
    0.46
    鮋
    0.46
    WeekDates
    0.46
     Fees
    0.46
    avacanam
    0.46
     fees
    0.46
     perguntas
    0.46
    Act Density 0.000%

    No Known Activations