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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords and function declarations

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

    Code block beginnings (if, class, def)

    np_acts-logits-general · gemini-2.0-flash

    code blocks and function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.49
    $
    -0.48
    하면
    -0.48
    findpost
    -0.47
    圳
    -0.47
     appelez
    -0.46
    NewRow
    -0.46
    istoitu
    -0.45
     nuages
    -0.43
    Về
    -0.43
    POSITIVE LOGITS
     "..\..\..\
    0.76
     "..\..\
    0.70
     <<<<<<<<<<<<<<
    0.66
    def
    0.64
    Jeografia
    0.63
    InvalidProtocol
    0.62
    setupUi
    0.62
     doInBackground
    0.61
    :✨
    0.60
    󠁢
    0.59
    Act Density 0.037%

    No Known Activations