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

    Neuronpedia

    INDEX
    Explanations

    elements of structured data, such as JSON or class definitions

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

    Code snippets or class definitions

    np_acts-logits-general · gemini-2.0-flash

    code block terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.86
     surla
    -0.78
    rungsseite
    -0.75
     Paglinawan
    -0.74
    ConstraintMaker
    -0.73
    IndentedString
    -0.73
     nahilalakip
    -0.69
    invokeLater
    -0.68
     صوتيه
    -0.67
    Билгалдахарш
    -0.66
    POSITIVE LOGITS
    [toxicity=0]
    0.53
        
    0.50
    enumi
    0.46
    ↵↵↵
    0.45
    multirow
    0.45
    ovan
    0.44
       
    0.44
    存于互联网档案馆
    0.43
    0.43
     Anyway
    0.42
    Act Density 0.384%
    No Known Activations