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

    Neuronpedia

    INDEX
    Explanations

    installing packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    습니다
    0.93
    baixo
    0.82
    ﮕ
    0.76
     facet
    0.75
    ɢ
    0.74
     chanc
    0.74
    ी
    0.70
    ামাক
    0.69
     nugget
    0.68
    सभा
    0.68
    POSITIVE LOGITS
    一股
    0.83
    $\$
    0.74
    ل
    0.69
    º
    0.66
    unlike
    0.66
    шому
    0.65
    バイル
    0.64
     벗
    0.62
    म
    0.62
    ্বাদ
    0.60
    Act Density 0.247%

    No Known Activations