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

    Neuronpedia

    INDEX
    Explanations

    describing current running small

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㡀
    0.46
     አይደ
    0.42
    Team
    0.42
     親
    0.41
    通貨
    0.41
    ቶችን
    0.40
    чыць
    0.40
    NOTES
    0.40
     ඔහුගේ
    0.40
    含ま
    0.39
    POSITIVE LOGITS
    akath
    0.51
    ão
    0.50
    ulação
    0.47
     cerrado
    0.43
    aculate
    0.43
    wens
    0.42
    统一
    0.42
     CGSize
    0.42
     тази
    0.41
    ین
    0.41
    Act Density 0.003%

    No Known Activations