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

    Neuronpedia

    INDEX
    Explanations

    programming and coding-related terms, specifically focusing on syntax and data handling operations

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

    Code, numbers, and technical terms

    np_acts-logits-general · gemini-2.0-flash

    digits and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    createServer
    -0.67
    TagMode
    -0.57
    ourage
    -0.55
    🦃
    -0.53
     Michaelis
    -0.52
    estacks
    -0.52
    WebElementEntity
    -0.52
    MLE
    -0.51
     Cabot
    -0.51
    InjectAttribute
    -0.51
    POSITIVE LOGITS
     digits
    0.78
    Digits
    0.74
     digit
    0.73
    Digit
    0.72
    digit
    0.70
    digits
    0.66
     Digit
    0.65
    验证码
    0.63
    memoized
    0.61
     Verification
    0.61
    Act Density 0.180%

    No Known Activations