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
     les
    -0.07
     pageCount
    -0.06
    층
    -0.06
     �
    -0.06
    .Flat
    -0.06
     Hồng
    -0.06
    Rail
    -0.06
    .iterator
    -0.06
     ary
    -0.06
     SimpleDateFormat
    -0.06
    POSITIVE LOGITS
    iris
    0.06
    /↵↵↵
    0.06
    _frame
    0.06
    friend
    0.06
     Moss
    0.06
    uffed
    0.06
    农
    0.06
     Acres
    0.06
    _reduction
    0.06
    =train
    0.06
    Act Density 0.009%

    No Known Activations