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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Third
    0.80
    a
    0.75
    例如
    0.71
    ور
    0.69
    See
    0.68
    шно
    0.68
    er
    0.67
    ؑ
    0.67
    在
    0.66
     메뉴
    0.65
    POSITIVE LOGITS
     emitida
    0.88
     infectious
    0.86
     potted
    0.83
     Tử
    0.83
     эти
    0.77
     pali
    0.77
     revolutionary
    0.77
    ipe
    0.75
     bikini
    0.75
     विद्य
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.