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

    Neuronpedia

    INDEX
    Explanations

    vocals and iconic figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()[
    0.41
    Input
    0.40
    ()
    0.40
     screenshot
    0.40
    ')[
    0.40
     upregulated
    0.40
    স্‌
    0.40
    String
    0.40
    Value
    0.39
    Number
    0.39
    POSITIVE LOGITS
     BOOKS
    0.46
     books
    0.45
     meeste
    0.45
     Coolidge
    0.45
     antigua
    0.44
    稒
    0.43
    الأ
    0.43
     禁止
    0.43
     cæ
    0.42
     eftersom
    0.42
    Act Density 0.001%

    No Known Activations