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

    Neuronpedia

    INDEX
    Explanations

    🔥 NEW! / read one by one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鸬
    0.45
    зиден
    0.42
     çıkarm
    0.41
    atth
    0.40
    يلات
    0.38
     Noz
    0.38
     wyp
    0.37
    ansı
    0.37
     Fitted
    0.36
    ментов
    0.36
    POSITIVE LOGITS
    ewe
    0.49
    وە
    0.48
    ەوە
    0.46
    ێت
    0.39
     reviews
    0.38
    reviews
    0.38
     pl
    0.38
    𝗧
    0.38
    OrElse
    0.37
    投注
    0.36
    Act Density 0.000%

    No Known Activations