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

    Neuronpedia

    INDEX
    Explanations

    lecture notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    au
    1.00
    ications
    1.00
    다
    0.96
    agian
    0.95
    າ
    0.95
     rozwiąz
    0.94
    多く
    0.92
    ata
    0.92
    ong
    0.91
    garian
    0.91
    POSITIVE LOGITS
    મ
    1.29
    P
    1.26
     lectures
    1.13
    יות
    1.11
    ن
    1.09
    w
    1.08
    x
    1.06
    on
    1.05
    К
    1.05
    У
    0.98
    Act Density 0.003%

    No Known Activations