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

    Neuronpedia

    INDEX
    Explanations

    make Python

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пь
    0.52
     polarity
    0.52
    hall
    0.50
     죄
    0.50
    шен
    0.50
    ዶ
    0.50
    шым
    0.49
    얄
    0.49
    riam
    0.48
    pF
    0.48
    POSITIVE LOGITS
     ngày
    0.46
    ></
    0.44
    目录下
    0.42
     gesund
    0.41
     دوسروں
    0.41
     والك
    0.40
     Versions
    0.40
    温
    0.40
    outine
    0.40
     ई
    0.39
    Act Density 0.004%

    No Known Activations