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

    Neuronpedia

    INDEX
    Explanations

    syntactical structures and programming language elements within code snippets

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

    Code-related punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    placeholders and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AlterField
    -0.72
     виправивши
    -0.66
    حوالہ
    -0.65
    참고
    -0.64
    AnchorStyles
    -0.62
     >=",
    -0.62
    elerik
    -0.62
     مرئيه
    -0.60
     cref
    -0.58
    hamshire
    -0.58
    POSITIVE LOGITS
     TBD
    0.80
    <eos>
    0.78
    TBD
    0.74
    (){}
    0.73
    ){}
    0.71
     TODO
    0.71
    TODO
    0.69
     NotImplemented
    0.68
     TBA
    0.62
     nothing
    0.61
    Act Density 0.191%

    No Known Activations