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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    as
    1.13
    ાર
    1.02
    ﺔ
    0.98
    un
    0.94
    ﺪ
    0.94
    ার
    0.92
    o
    0.92
     bilingual
    0.90
    _,
    0.89
     बल्कि
    0.89
    POSITIVE LOGITS
    드
    1.27
     Stück
    1.23
    "."
    1.23
    楊
    1.19
    ഹ്ലാദ
    1.18
     jalan
    1.17
     (\%)
    1.17
    드의
    1.14
    드가
    1.13
     ڈاؤن
    1.13
    Act Density 0.000%

    No Known Activations