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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic and scientific research fields

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

    foreign words in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gild
    -0.54
    parsedMessage
    -0.52
    AddHtmlAttribute
    -0.49
     Div
    -0.48
     fc
    -0.47
    Jereo
    -0.46
    oplayer
    -0.45
     lenker
    -0.45
     FAS
    -0.45
     fg
    -0.45
    POSITIVE LOGITS
     šķ
    0.62
     vä
    0.60
     aikaa
    0.60
     inalámbrica
    0.60
     vastaan
    0.59
     wereld
    0.58
     desierto
    0.57
     savaş
    0.57
     blessés
    0.57
     maail
    0.56
    Act Density 0.003%

    No Known Activations