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

    Neuronpedia

    INDEX
    Explanations

    deductive reasoning syllogisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.68
    ल
    0.64
    м
    0.62
     his
    0.61
    لیک
    0.61
    ER
    0.60
    мма
    0.57
     Apple
    0.54
    ل
    0.54
    чки
    0.54
    POSITIVE LOGITS
    timing
    0.56
     منابع
    0.56
    事的
    0.55
    industrie
    0.55
     चौथा
    0.55
     patru
    0.54
    estimated
    0.54
    fifths
    0.54
     pracę
    0.54
     получение
    0.53
    Act Density 0.017%

    No Known Activations