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

    Neuronpedia

    INDEX
    Explanations

    declarations and definitions of functions in code snippets

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

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     подо
    -0.29
     Both
    -0.28
    ствует
    -0.27
     All
    -0.26
     encourages
    -0.26
     zároveň
    -0.26
     vytvoř
    -0.26
     former
    -0.25
     stát
    -0.25
    ۜ
    -0.25
    POSITIVE LOGITS
     ſind
    0.73
    parsedMessage
    0.69
    出版年
    0.68
     queſta
    0.68
     iſt
    0.67
     AppCompatTheme
    0.67
    astéroïdes
    0.66
    <unused80>
    0.65
     好文分享
    0.65
    <unused8>
    0.65
    Act Density 0.064%

    No Known Activations