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

    Neuronpedia

    INDEX
    Explanations

    foreign texts and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     첨
    0.46
     দ্রব
    0.43
     원하는
    0.43
     کە
    0.42
     가능한
    0.41
     도로
    0.40
     হাজারের
    0.40
     ブリヂストン
    0.39
    compiler
    0.39
     کولی
    0.39
    POSITIVE LOGITS
    ா
    0.48
    ា
    0.48
    Trong
    0.46
     दुर्गेश
    0.44
    他
    0.44
    唐
    0.44
    Johnson
    0.44
     Sonntag
    0.43
    Hari
    0.43
    我
    0.43
    Act Density 0.000%

    No Known Activations