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
    我
    0.43
    eigen
    0.42
    عت
    0.39
     FileInputStream
    0.39
     самые
    0.39
     вот
    0.39
     நான்
    0.39
    бе
    0.38
    澤
    0.37
    Фа
    0.37
    POSITIVE LOGITS
     francês
    0.50
    URAL
    0.48
     gud
    0.48
    ভূম
    0.48
     mendatang
    0.47
    녔
    0.47
     pozwala
    0.47
    鹉
    0.47
    šć
    0.46
     rétréc
    0.46
    Act Density 0.001%

    No Known Activations