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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    事に
    0.43
     mainly
    0.43
     primarily
    0.41
     humiliated
    0.41
    primarily
    0.40
     principalement
    0.39
    មក
    0.39
    ക്കുകയും
    0.38
    ceq
    0.38
     पाण
    0.38
    POSITIVE LOGITS
     אח
    0.49
     альбо
    0.46
    你自己
    0.45
    বিহীন
    0.45
     можно
    0.44
     אל
    0.44
    દાર
    0.43
     그대로
    0.43
    ాన్ని
    0.43
    ์
    0.42
    Act Density 0.002%

    No Known Activations