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

    Neuronpedia

    INDEX
    Explanations

    code snippets that include URLs, regular expressions, and the word "github"

    oai_token-act-pair · gemini-2.0-flash

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.58
    '
    -0.69
    *
    -0.53
     AT
    -0.51
     Bourgoin
    -0.49
    #
    -0.49
    AT
    -0.48
    şiv
    -0.48
    IUrlHelper
    -0.46
    _
    -0.46
    POSITIVE LOGITS
     StatefulWidget
    0.71
    AxisAlignment
    0.64
     nationaux
    0.64
    urlpatterns
    0.64
     contextLoads
    0.63
     maxn
    0.62
     onBackPressed
    0.62
     depositphotos
    0.61
    mybatisplus
    0.60
     xmm
    0.60
    Act Density 2.157%

    No Known Activations