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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lampang
    0.89
     inclu
    0.78
     irm
    0.77
     alde
    0.76
    ﺒ
    0.76
     kõige
    0.73
     இங்கே
    0.72
     oce
    0.72
     встречи
    0.72
    ండి
    0.71
    POSITIVE LOGITS
    ת
    1.00
    al
    0.92
    ल
    0.78
    N
    0.78
    ج
    0.75
    على
    0.73
    不必
    0.73
    d
    0.73
    m
    0.71
    le
    0.71
    Act Density 0.001%

    No Known Activations