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

    Neuronpedia

    INDEX
    Explanations

    addEventListener usage and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を表示
    1.91
    }";
    1.80
     peeled
    1.72
     इसमें
    1.63
     unten
    1.63
    ্দ্র
    1.62
     що
    1.59
    }");
    1.58
    АР
    1.56
    你要
    1.54
    POSITIVE LOGITS
    in
    1.70
    al
    1.54
    zona
    1.52
    as
    1.48
     propriedades
    1.43
     সর্বো
    1.39
    <>());
    1.38
     propriedade
    1.33
    m
    1.29
    tting
    1.29
    Act Density 0.000%

    No Known Activations