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

    Neuronpedia

    INDEX
    Explanations

    numerical references and citations within the text

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

    figures, algorithms, or tables

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.76
     doInBackground
    -0.73
    AddHtmlAttribute
    -0.72
    posedge
    -0.62
    LikeLiked
    -0.60
    Hozzáférés
    -0.59
     réessayer
    -0.58
     بتاريخ
    -0.58
    WireFormat
    -0.57
     Paglinawan
    -0.56
    POSITIVE LOGITS
    ########.
    0.52
     phép
    0.50
    ("");
    0.47
    かわらず
    0.47
     {},
    0.46
    ξ
    0.46
    حوالہ
    0.45
    toggler
    0.45
    croft
    0.43
     TCL
    0.43
    Act Density 0.378%

    No Known Activations