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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    드가
    0.79
    penas
    0.79
    ddar
    0.78
    드의
    0.77
     Той
    0.76
    트워크
    0.75
     D
    0.73
    드를
    0.73
    개가
    0.72
    왤
    0.71
    POSITIVE LOGITS
     integers
    1.45
    整数
    1.23
     integer
    1.17
    数字
    1.13
     numerals
    1.13
     numbers
    1.12
    數字
    1.08
     чисел
    1.05
     숫자
    1.05
     digits
    1.05
    Act Density 0.991%

    No Known Activations