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

    Neuronpedia

    INDEX
    Explanations

    lead or advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мимо
    0.71
     failures
    0.69
    작
    0.68
    व्यों
    0.64
    ثناء
    0.62
    簸
    0.62
     tác
    0.62
    ility
    0.62
    عان
    0.61
     작동
    0.61
    POSITIVE LOGITS
     lead
    1.43
    lead
    1.30
    Lead
    1.27
     Lead
    1.25
     बढ़त
    1.25
    领先
    1.21
     leads
    1.21
     ventaja
    1.19
    leads
    1.14
     vantaggio
    1.14
    Act Density 0.046%

    No Known Activations