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

    Neuronpedia

    INDEX
    Explanations

    higher upfront, wage, production, growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.77
    لي
    0.70
    し
    0.68
    드
    0.66
    ام
    0.63
    ك
    0.63
    ين
    0.63
    يع
    0.62
    }).
    0.61
    ون
    0.59
    POSITIVE LOGITS
    .
    0.64
    I
    0.62
    t
    0.61
    u
    0.59
     higher
    0.58
     volatility
    0.57
    nya
    0.56
    ing
    0.55
    '
    0.54
     risk
    0.52
    Act Density 0.267%

    No Known Activations