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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Issues
    0.46
     complicating
    0.46
    Issues
    0.45
     возникновения
    0.44
     алуу
    0.44
    引入
    0.44
    CriteriaUtils
    0.44
    choices
    0.42
    优化
    0.42
     Concerns
    0.41
    POSITIVE LOGITS
     naph
    0.42
     sk
    0.41
     leather
    0.40
    ೆಂದು
    0.40
    عرف
    0.39
     dimiliki
    0.39
     simulator
    0.39
     naked
    0.38
    enen
    0.38
     ruler
    0.38
    Act Density 0.013%

    No Known Activations