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

    Neuronpedia

    INDEX
    Explanations

    numbers, particularly those associated with statistical data and results

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

    Numbers in brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jefus
    -0.65
     :—
    -0.59
    rungsseite
    -0.59
    verifyException
    -0.58
     Cater
    -0.57
    sinon
    -0.57
     loadImage
    -0.56
     Chriftian
    -0.55
     Chrift
    -0.53
     ftill
    -0.53
    POSITIVE LOGITS
    AutoScale
    0.62
    SourceChecksum
    0.57
    InjectAttribute
    0.56
     MenuView
    0.54
    WireFormat
    0.54
     resourceCulture
    0.54
     Paglinawan
    0.52
    IUrlHelper
    0.50
    Viited
    0.50
     ujednoznacz
    0.49
    Act Density 0.212%

    No Known Activations