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

    Neuronpedia

    INDEX
    Explanations

    code blocks, possibly definitions of functions or classes

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.69
    +#+#
    -0.69
     pinulongan
    -0.67
     CreateTagHelper
    -0.65
     المعيارى
    -0.64
    libft
    -0.59
     capital
    -0.58
     EconPapers
    -0.57
    anstal
    -0.57
    原始内容存档于
    -0.56
    POSITIVE LOGITS
    <bos>
    1.65
    engeti
    0.51
     Gogh
    0.47
    phère
    0.46
    idends
    0.45
     venden
    0.45
    ULTURE
    0.44
    ividu
    0.44
    '
    0.44
    {!!
    0.44
    Act Density 0.750%

    No Known Activations