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

    Neuronpedia

    INDEX
    Explanations

    periods in a sequence of code or text

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

    code imports and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.73
    /***/
    -0.69
    ScopeManager
    -0.63
     الحره
    -0.61
    __;
    -0.59
    apimachinery
    -0.58
     ModelExpression
    -0.58
    ✨:
    -0.57
     متعلقه
    -0.57
    __);
    -0.57
    POSITIVE LOGITS
    RuntimeObject
    0.33
     africain
    0.32
     évêque
    0.29
     appui
    0.29
     geçi
    0.28
     puestos
    0.28
     africains
    0.28
     menengah
    0.27
     lecteur
    0.27
     censiti
    0.26
    Act Density 0.008%

    No Known Activations