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

    Neuronpedia

    INDEX
    Explanations

    LaTeX math notation

    oai_token-act-pair · gemini-2.0-flash

    non-English words or symbols

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

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.83
     $\
    -0.70
     ${\
    -0.64
     ${
    -0.60
    urtstag
    -0.59
     Gri
    -0.57
    dibles
    -0.57
     }}{\
    -0.57
    contentLoaded
    -0.55
    writeField
    -0.54
    POSITIVE LOGITS
    önster
    0.50
    tagHelperRunner
    0.50
    Переваги
    0.48
     abbildung
    0.48
    发表于
    0.47
     ragaz
    0.47
    السكان
    0.47
     Powered
    0.46
    ailangan
    0.46
    WHM
    0.46
    Act Density 8.501%

    No Known Activations