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

    Neuronpedia

    INDEX
    Explanations

    d<number>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chhoti
    0.94
     Еще
    0.88
     charmed
    0.80
     باقي
    0.79
    횐
    0.77
    माइंडर
    0.77
    薁
    0.74
    gqlgen
    0.73
     madad
    0.73
     Wight
    0.72
    POSITIVE LOGITS
    ism
    0.85
    кі
    0.78
    ard
    0.72
     transcendence
    0.71
    က
    0.71
    att
    0.71
    со
    0.71
    ви
    0.69
     piecewise
    0.66
    风险
    0.65
    Act Density 0.000%

    No Known Activations