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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🔈
    0.39
    следова
    0.38
    Pins
    0.38
    Источник
    0.38
    ✒
    0.37
     тў
    0.37
    рито
    0.36
     ""<
    0.36
    坌
    0.35
    وزیشن
    0.34
    POSITIVE LOGITS
     WEEK
    0.36
    thers
    0.35
     weekends
    0.35
     Week
    0.35
    ineties
    0.34
     week
    0.34
     others
    0.34
    vers
    0.33
     rub
    0.33
     Oggi
    0.33
    Act Density 0.013%

    No Known Activations