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

    Neuronpedia

    INDEX
    Explanations

    short,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     black
    0.52
     splash
    0.50
     Middle
    0.50
     full
    0.49
     Big
    0.49
    ad
    0.49
     BA
    0.49
     l
    0.49
    at
    0.47
    ak
    0.47
    POSITIVE LOGITS
    kjhtml
    0.52
     sucks
    0.52
     postérieurs
    0.51
    有趣
    0.48
    礽
    0.48
    세요
    0.47
    стям
    0.46
    幄
    0.46
    삵
    0.46
    ソース
    0.46
    Act Density 0.000%

    No Known Activations