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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters used in programming syntax

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

    Code, versions, and file paths

    np_acts-logits-general · gemini-2.0-flash

    ignoreversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ($
    -0.51
     Ruff
    -0.47
    bus
    -0.47
    Rifer
    -0.46
     TAX
    -0.44
    bal
    -0.44
    tech
    -0.44
    ÔNG
    -0.43
    ($
    -0.42
    πουργ
    -0.41
    POSITIVE LOGITS
    ViewFeatures
    1.00
    LookAnd
    0.95
    SourceChecksum
    0.91
     pinulongan
    0.85
    EndInit
    0.80
    InjectAttribute
    0.74
    ↵
    0.72
    httphttps
    0.72
    Espèce
    0.72
     onAnimation
    0.69
    Act Density 0.187%

    No Known Activations