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

    Neuronpedia

    INDEX
    Explanations

    a combination of numbers and other symbols.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and specific identifiers

    np_token-act-pair-logits · gpt-4o-mini

    Technical and numerical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     himo
    -0.60
     secondary
    -0.50
    λεκ
    -0.48
     Secondary
    -0.48
    Secondary
    -0.46
    Portail
    -0.46
     SECONDARY
    -0.46
     समीक्षाओं
    -0.46
    awtextra
    -0.45
     Doub
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.66
    RegressionTest
    0.59
    Архівовано
    0.56
     single
    0.56
    AutoresizingMask
    0.55
     مشين
    0.54
     aja
    0.52
    posedge
    0.52
     únicos
    0.51
     ONE
    0.51
    Act Density 2.593%

    No Known Activations