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

    Neuronpedia

    INDEX
    Explanations

    mentions of content types and encodings, especially in the context of web requests and parsing.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dziew
    -0.42
     varm
    -0.39
     p
    -0.38
    bagian
    -0.37
    حسب
    -0.36
     teljes
    -0.35
     نویس
    -0.35
    <bos>
    -0.35
    Sharper
    -0.35
     majd
    -0.34
    POSITIVE LOGITS
    featureID
    0.87
     autorytatywna
    0.85
    PreferredItem
    0.81
     Roskov
    0.81
     ujednoznacz
    0.80
    ագրություններ
    0.79
     kasarigan
    0.79
    tagHelperRunner
    0.73
    AndEndTag
    0.72
     intptr
    0.72
    Act Density 1.829%

    No Known Activations