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

    Neuronpedia

    INDEX
    Explanations

    who's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    也会
    -2.17
    푙
    -2.06
    g
    -2.03
    嗩
    -2.03
    1
    -2.02
    ”。
    -2.02
    擽
    -1.95
     января
    -1.88
    啣
    -1.84
    衎
    -1.83
    POSITIVE LOGITS
    2.23
    providedIn
    2.20
     been
    2.14
    -
    1.91
    持つ
    1.91
     撮っ
    1.83
     руках
    1.78
     \
    1.78
    '
    1.77
    canActivate
    1.71
    Act Density 0.003%

    No Known Activations