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

    Neuronpedia

    INDEX
    Explanations

    bullet points and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     등의
    0.89
     등
    0.87
     등이
    0.78
     etc
    0.74
     liệu
    0.73
    とか
    0.71
    etc
    0.70
     adlı
    0.67
    쪽
    0.67
     쪽
    0.66
    POSITIVE LOGITS
    :‏
    1.05
    涫
    1.03
    wpilib
    1.02
    :|
    1.01
     CONSIDER
    1.00
     |”
    0.98
    Consider
    0.98
     JANUARY
    0.97
    Im
    0.97
    闶
    0.97
    Act Density 0.621%

    No Known Activations