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

    Neuronpedia

    INDEX
    Explanations

    key improvements and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zych
    0.39
    asie
    0.33
    iconductor
    0.33
    гно
    0.33
    dre
    0.33
    IGER
    0.33
    olit
    0.33
    lada
    0.33
    ugly
    0.32
    扈
    0.32
    POSITIVE LOGITS
     improvements
    0.61
     mejoras
    0.52
     Improvements
    0.50
     improvement
    0.49
     takeaways
    0.48
    Improvements
    0.47
    ポイント
    0.46
    improvements
    0.46
     features
    0.46
     개선
    0.44
    Act Density 0.004%

    No Known Activations