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

    Neuronpedia

    INDEX
    Explanations

    examples and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     കട
    0.41
    店舗
    0.38
     উল্ল
    0.37
    idded
    0.36
    utar
    0.36
    ⃖
    0.35
     бага
    0.35
    スポーツ
    0.35
     tokom
    0.35
    交通事故
    0.35
    POSITIVE LOGITS
    Gordon
    0.41
     had
    0.41
     waarvan
    0.40
    Ha
    0.39
    Superior
    0.39
    睺
    0.38
     Gordon
    0.38
     निशाने
    0.38
    Von
    0.37
     മീഡിയ
    0.37
    Act Density 0.155%

    No Known Activations