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

    Neuronpedia

    INDEX
    Explanations

    works by women

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     who
    -1.47
    obrá
    -1.39
     yesterday
    -1.34
    なのです
    -1.31
     formerly
    -1.27
    ଵ
    -1.26
    を中心に
    -1.23
    で見る
    -1.23
     ранее
    -1.21
    ございません
    -1.21
    POSITIVE LOGITS
     again
    1.45
     igjen
    1.20
     další
    1.19
    อีก
    1.18
    Ս
    1.16
    Islamic
    1.15
    เหรียญ
    1.14
     suoi
    1.13
    ชุด
    1.10
    логии
    1.07
    Act Density 0.031%

    No Known Activations