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

    Neuronpedia

    INDEX
    Explanations

    over a period of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    那边
    0.52
    阐
    0.46
     способов
    0.45
    ként
    0.43
    这边
    0.43
     எ
    0.41
     Ways
    0.40
     সৈন্য
    0.40
     expression
    0.39
     Serum
    0.39
    POSITIVE LOGITS
    期間
    0.88
     periode
    0.88
    기간
    0.86
     기간
    0.86
     период
    0.85
     period
    0.84
     Zeitraum
    0.80
     période
    0.79
     período
    0.79
    period
    0.77
    Act Density 0.056%

    No Known Activations