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

    Neuronpedia

    INDEX
    Explanations

    my/our

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -1.05
    AnchorTagHelper
    -0.75
    RenderAtEndOf
    -0.74
     سكانية
    -0.71
    TypedDataSet
    -0.70
    AddTagHelper
    -0.69
    OGND
    -0.69
    awtextra
    -0.66
     EconPapers
    -0.66
    IsContent
    -0.64
    POSITIVE LOGITS
     humble
    0.73
     honest
    0.57
    humble
    0.56
     humilde
    0.55
     opp
    0.52
     option
    0.51
     respectful
    0.49
    honest
    0.46
     humb
    0.46
     understanding
    0.45
    Act Density 0.002%

    No Known Activations