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

    Neuronpedia

    INDEX
    Explanations

    programming language components and structures, particularly related to function definitions and calls

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

    Code, math, and unusual symbols/punctuation

    np_acts-logits-general · gemini-2.0-flash

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.73
      
    -0.53
     he
    -0.48
     ragazzo
    -0.45
     ,
    -0.44
     my
    -0.44
     I
    -0.43
     ő
    -0.42
     polvere
    -0.41
     numOf
    -0.41
    POSITIVE LOGITS
     AspNetCore
    1.16
     ModelExpression
    1.08
     autorytatywna
    1.03
    1.02
     للمعارف
    1.02
     كومونز
    1.00
    Personendaten
    0.99
    ✨:
    0.99
     שוליים
    0.99
     חיצוניים
    0.96
    Act Density 1.280%

    No Known Activations