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

    Neuronpedia

    INDEX
    Explanations

    skewness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dyby
    -0.08
     sonra
    -0.08
     потім
    -0.08
    اورپ
    -0.07
    ulta
    -0.07
    atro
    -0.07
     ニ
    -0.07
     unnoticed
    -0.07
     наличи
    -0.07
    ौज
    -0.07
    POSITIVE LOGITS
     skew
    0.15
     skewed
    0.13
     See
    0.06
     KNOW
    0.06
     swirl
    0.06
     skulls
    0.06
    _mul
    0.06
     look
    0.06
     kill
    0.06
     Sk
    0.06
    Act Density 0.001%

    No Known Activations