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

    Neuronpedia

    INDEX
    Explanations

    numbers preceding names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ९
    0.45
     نوشت
    0.43
     هستیم
    0.42
    wikipedia
    0.41
     fift
    0.40
    rectangular
    0.40
    二维
    0.40
     الزاويه
    0.40
    twenty
    0.39
    升级
    0.39
    POSITIVE LOGITS
    氅
    0.41
     Place
    0.39
    そもそも
    0.39
    用品
    0.38
    cipe
    0.38
     Determ
    0.37
     Bagaimana
    0.37
    гия
    0.36
     एक्चुअली
    0.36
    rimer
    0.36
    Act Density 0.010%

    No Known Activations