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

    Neuronpedia

    INDEX
    Explanations

    numerical data and dates in the text

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

    Dates appearing with a number

    np_acts-logits-general · gemini-2.0-flash

    months and days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     szóci
    -0.52
     just
    -0.51
     does
    -0.50
    netinet
    -0.49
    SearchTree
    -0.49
     $
    -0.47
    <eos>
    -0.47
     on
    -0.46
    ↵↵
    -0.46
     about
    -0.45
    POSITIVE LOGITS
    存于互联网档案馆
    0.90
    Kaynakça
    0.86
    HtmlAttribute
    0.86
    AndEndTag
    0.81
     fevere
    0.75
     iſt
    0.75
    SourceChecksum
    0.74
    脚注の使い方
    0.74
    
    0.73
    LookAnd
    0.72
    Act Density 0.160%

    No Known Activations