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

    Neuronpedia

    INDEX
    Explanations

    datetime formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wagner
    0.41
     الأعلى
    0.38
     Wagner
    0.37
    队列
    0.37
    Harmony
    0.37
    Portfolio
    0.36
    ৎস্য
    0.36
    ▐
    0.35
     очередь
    0.35
    Nak
    0.35
    POSITIVE LOGITS
     moment
    1.34
     Moment
    1.30
    moment
    1.26
    Moment
    1.06
     Moments
    1.05
     moments
    1.03
     momento
    1.01
     момент
    0.97
     момента
    0.97
     DateTime
    0.90
    Act Density 0.197%

    No Known Activations