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

    Neuronpedia

    INDEX
    Explanations

    version numbers and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arabangsa
    0.42
    τηση
    0.42
    خستان
    0.42
    بل
    0.41
    ционер
    0.41
    guez
    0.41
    榭
    0.41
    isyen
    0.40
    羍
    0.40
    чиго
    0.40
    POSITIVE LOGITS
    }$=
    0.50
     ताज
    0.46
     voit
    0.44
     обладают
    0.43
     Obtaining
    0.42
    logger
    0.41
     $=$
    0.41
     ਹੀ
    0.40
    इंटर
    0.40
     обладает
    0.39
    Act Density 0.000%

    No Known Activations