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

    Neuronpedia

    INDEX
    Explanations

    negation, incorrect, strong sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ریت
    0.58
    标注
    0.48
    0.48
    ری
    0.47
    ρι
    0.46
    苄
    0.46
    邳
    0.46
    회를
    0.45
    キーワード
    0.45
    ată
    0.44
    POSITIVE LOGITS
     offent
    0.50
    lowski
    0.48
    fear
    0.46
     unn
    0.46
    faux
    0.45
    fuck
    0.45
    Fuck
    0.44
     hysteria
    0.44
     मनु
    0.43
     ఎలా
    0.43
    Act Density 0.003%

    No Known Activations