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

    Neuronpedia

    INDEX
    Explanations

    import cv2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    য়ায়
    0.38
    เภท
    0.38
    驄
    0.38
    ListName
    0.37
    业务
    0.37
     মিলি
    0.37
    塞尔
    0.36
    钀
    0.36
    ヒト
    0.35
     trấn
    0.35
    POSITIVE LOGITS
     edit
    0.43
     lambda
    0.41
     precedent
    0.40
     tit
    0.40
     editing
    0.40
     precedence
    0.39
     multiplier
    0.38
     writing
    0.38
     carpenters
    0.38
     parenthesis
    0.37
    Act Density 0.003%

    No Known Activations