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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names followed by actions or specific identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.79
    IndentedString
    -0.67
    -------
    -0.61
    <bos>
    -0.59
    LayoutConstraint
    -0.59
    🟤
    -0.57
    ]=>
    -0.57
    SPONSORED
    -0.57
    HomeAsUpEnabled
    -0.56
    windowFixed
    -0.56
    POSITIVE LOGITS
    Bài
    1.08
     bài
    0.97
     Bài
    0.94
    bài
    0.76
     article
    0.52
     Article
    0.48
    Day
    0.47
     câu
    0.47
    Câu
    0.47
    Article
    0.46
    Act Density 0.003%

    No Known Activations