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

    Neuronpedia

    INDEX
    Explanations

    technical terms and nomenclature related to programming or systems

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

    Non-English characters and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.82
    DoubleQuotes
    -0.73
     }{@
    -0.69
    awtextra
    -0.68
    principalColumn
    -0.67
    Autoritní
    -0.65
     الحره
    -0.63
    PointerException
    -0.63
     שוליים
    -0.59
    ValueStyle
    -0.59
    POSITIVE LOGITS
    wapV
    0.43
      
    0.35
     vell
    0.35
    ürgen
    0.35
     tv
    0.34
     fais
    0.33
     integri
    0.33
     comunic
    0.33
     pann
    0.31
     Integration
    0.31
    Act Density 0.857%

    No Known Activations