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

    Neuronpedia

    INDEX
    Explanations

    ellipsis and related punctuation or formatting in text

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

    "... Read" pattern

    np_acts-logits-general · gemini-2.0-flash

    read our full review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wikidata
    -0.54
     InputDecoration
    -0.51
    EndContext
    -0.50
     layui
    -0.48
     dem
    -0.47
    EntityFramework
    -0.46
    lloworld
    -0.46
    出版年
    -0.46
    ématiques
    -0.46
    cyd
    -0.45
    POSITIVE LOGITS
     Roskov
    0.86
    oredCriteria
    0.83
    Tembelea
    0.69
    DockStyle
    0.69
    <eos>
    0.68
    SourceChecksum
    0.68
     Paglinawan
    0.65
    ..."
    0.64
     myſelf
    0.63
    :✨
    0.62
    Act Density 0.096%

    No Known Activations