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

    Neuronpedia

    INDEX
    Explanations

    fight dirty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಪೆ
    0.49
     कार्यक्रमा
    0.47
    ινε
    0.46
    <0xE1>
    0.43
    enzie
    0.43
    趾
    0.42
    その他の
    0.42
     سایر
    0.42
    オー
    0.41
     дорогие
    0.41
    POSITIVE LOGITS
     intended
    0.47
     violation
    0.42
     sida
    0.42
     vi
    0.41
     nginx
    0.41
     logic
    0.41
     dangereux
    0.40
     loosening
    0.40
     violations
    0.39
     dangerously
    0.39
    Act Density 0.004%

    No Known Activations