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

    Neuronpedia

    INDEX
    Explanations

    special characters and mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.59
     of
    0.57
    को
    0.57
    h
    0.57
    د
    0.57
    א
    0.57
    d
    0.55
    이
    0.55
    ע
    0.55
    この
    0.55
    POSITIVE LOGITS
    ла
    0.54
    ci
    0.46
    ového
    0.42
    ovaný
    0.42
    ль
    0.42
    اسية
    0.41
    .
    0.40
    рд
    0.40
    ads
    0.39
    cknowled
    0.39
    Act Density 0.497%

    No Known Activations