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

    Neuronpedia

    INDEX
    Explanations

    references to "D" notation or labels in technical contexts

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

    Token D followed by a period or other punctuation

    np_acts-logits-general · gemini-2.0-flash

    `D.` followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createState
    -0.61
    RenderAtEndOf
    -0.61
    -0.59
    Bathrooms
    -0.55
    Externé
    -0.55
     @}
    -0.52
    VersionUID
    -0.51
     kasarigan
    -0.51
     PyLong
    -0.50
    melte
    -0.50
    POSITIVE LOGITS
    Autoritní
    0.65
    ism
    0.54
    addGap
    0.51
     vermelhas
    0.50
    reise
    0.48
    LP
    0.48
    LS
    0.47
    izziness
    0.47
    הערות
    0.47
    SharedCtor
    0.46
    Act Density 0.246%

    No Known Activations