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

    Neuronpedia

    INDEX
    Explanations

    document structure elements, particularly titles and sections

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

    titles and headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.64
     beginnetje
    -0.59
     Италијани
    -0.58
    󠁴
    -0.57
    EndProject
    -0.57
     ویکی‌آمباردا
    -0.57
     bezeichneter
    -0.57
    NameInMap
    -0.56
     PagesJaunes
    -0.56
    ergies
    -0.55
    POSITIVE LOGITS
    title
    0.73
    Title
    0.73
     title
    0.68
     Title
    0.66
     AssemblyTitle
    0.60
    Título
    0.59
    TITLE
    0.59
    setTitle
    0.58
    <h1>
    0.56
     Titel
    0.55
    Act Density 0.004%

    No Known Activations