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

    Neuronpedia

    INDEX
    Explanations

    words that express relative quantity alongside the articles "a" or "an".

    oai_token-act-pair · gemini-2.0-flash

    articles and "more"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MLLoader
    -1.16
     سكانية
    -1.09
    Rhestr
    -1.09
    UrlResolution
    -1.01
    BufferException
    -0.94
     насељу
    -0.92
    principalColumn
    -0.92
    évaluateur
    -0.92
    UserScript
    -0.91
    CloseOperation
    -0.90
    POSITIVE LOGITS
    <bos>
    0.60
     "
    0.54
    ↵
    0.53
     
    0.52
    ,
    0.48
     F
    0.48
     a
    0.46
    e
    0.46
    ...
    0.46
    -
    0.46
    Act Density 4.271%

    No Known Activations