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

    Neuronpedia

    INDEX
    Explanations

    references to regulations and standards related to compliance and safety

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

    Tokens preceding guidelines or standards

    np_acts-logits-general · gemini-2.0-flash

    guidelines and standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.94
     AssemblyCulture
    -0.87
    ंदीखरीदारी
    -0.86
    aarrggbb
    -0.85
    ThroughAttribute
    -0.76
    曖昧さ回避
    -0.74
    省市镇
    -0.74
    IndentedString
    -0.73
    ArgsConstructor
    -0.70
     disambiguazione
    -0.70
    POSITIVE LOGITS
     guidelines
    1.19
     guidance
    1.09
     guide
    1.02
     Guide
    1.00
     Guidelines
    0.98
    Guide
    0.98
     guideline
    0.96
    guidelines
    0.95
    guidance
    0.93
     guides
    0.92
    Act Density 0.381%

    No Known Activations