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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    办法
    -0.08
    '),'
    -0.07
    　
    -0.06
    。それ
    -0.06
    .FloatField
    -0.06
    UPPORT
    -0.06
    ё
    -0.06
    (red
    -0.06
     되었
    -0.06
    ='./
    -0.06
    POSITIVE LOGITS
    Anchor
    0.07
     exceeding
    0.06
    ifications
    0.06
    tes
    0.06
    Veter
    0.06
    _twitter
    0.06
    -flat
    0.06
    می
    0.06
    oris
    0.06
    .lock
    0.06
    Act Density 0.006%

    No Known Activations