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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ------+------+
    -0.07
     Sal
    -0.06
    闻
    -0.06
    .embedding
    -0.06
     ней
    -0.06
    .DateFormat
    -0.06
     dưỡng
    -0.06
    �
    -0.06
     rebounds
    -0.06
     Decoration
    -0.06
    POSITIVE LOGITS
    _put
    0.07
    752
    0.06
    up
    0.06
    UP
    0.06
     Chap
    0.06
    .↵↵↵↵
    0.06
    apply
    0.06
     hog
    0.06
    ('<
    0.06
     миров
    0.06
    Act Density 0.094%

    No Known Activations