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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ählten
    0.46
     maggiore
    0.46
    msbuild
    0.44
    wiata
    0.44
    ‮
    0.44
     anvä
    0.44
    क्ति
    0.43
     انتخاب
    0.43
     المؤلف
    0.43
     små
    0.42
    POSITIVE LOGITS
     我们
    0.42
    chetto
    0.42
    ಿಸಿ
    0.41
    乎
    0.41
    ссмо
    0.40
    ಿಸ
    0.40
    รษฐกิจ
    0.40
    ದುಕ
    0.39
     MacL
    0.39
    御
    0.39
    Act Density 0.001%

    No Known Activations