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

    Neuronpedia

    INDEX
    Explanations

    margin : all None

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ישראל
    0.41
    ctuaries
    0.39
     Liste
    0.38
    ంబేద్కర్
    0.38
    ərbay
    0.38
     челу
    0.38
    zoomSeekBar
    0.38
    コンビニ
    0.38
    ocolate
    0.37
     महाविद्यालय
    0.37
    POSITIVE LOGITS
    App
    0.36
    前后
    0.34
    暴力
    0.32
     vra
    0.32
    обра
    0.31
     swap
    0.31
    ꜰ
    0.31
     diss
    0.30
     racism
    0.30
     humiliation
    0.30
    Act Density 0.001%

    No Known Activations