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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code

    oai_token-act-pair · gemini-2.0-flash

    usepackage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.69
    存于互联网档案馆
    -0.69
     ddelweddau
    -0.65
    rometry
    -0.64
    webElementGuid
    -0.63
    ConverterFactory
    -0.62
     NSCoder
    -0.61
    balleur
    -0.60
    ArgsConstructor
    -0.60
    Démographie
    -0.58
    POSITIVE LOGITS
    <bos>
    1.91
    The
    0.44
     run
    0.40
     move
    0.40
     the
    0.40
    An
    0.39
    Max
    0.37
    '
    0.36
    To
    0.36
    Ten
    0.36
    Act Density 0.174%

    No Known Activations