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

    Neuronpedia

    INDEX
    Explanations

    municipal code, exceptions, versatile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ꔹ
    0.50
    е
    0.49
    нг
    0.49
    粞
    0.48
    кс
    0.47
     ইয়াহিয়ার
    0.47
    ശ
    0.47
    lected
    0.47
    餉
    0.46
     PRESSURE
    0.46
    POSITIVE LOGITS
     be
    0.48
    展开
    0.43
     corpus
    0.43
     sound
    0.42
     dangling
    0.41
     brew
    0.41
     لعب
    0.41
     mif
    0.40
     يع
    0.40
    뷔
    0.39
    Act Density 0.001%

    No Known Activations