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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     количе
    0.82
     গেলেন
    0.73
     :=\
    0.70
     গেল
    0.68
    assertSame
    0.67
    ):=
    0.66
    ǰ
    0.66
     haline
    0.65
     گئی
    0.65
    有多少
    0.63
    POSITIVE LOGITS
     around
    2.71
    around
    2.34
     Around
    2.31
    Around
    2.29
     somewhere
    2.18
     intorno
    2.11
     alrededor
    2.03
     autour
    1.88
     closer
    1.84
     sekitar
    1.83
    Act Density 1.399%

    No Known Activations