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

    Neuronpedia

    INDEX
    Explanations

    tragic flaw, fate, and heroines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    1.26
    し
    1.02
    માં
    1.02
    ﺖ
    0.99
    ug
    0.99
    frac
    0.97
    ール
    0.94
    ut
    0.93
    ur
    0.92
    io
    0.89
    POSITIVE LOGITS
    。
    1.38
    .}
    1.19
    .
    1.18
    f
    1.15
    }
    1.09
    لي
    1.07
     traged
    1.07
    ।
    1.04
     可以
    0.98
    <0x0D>
    0.93
    Act Density 0.006%

    No Known Activations