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

    Neuronpedia

    INDEX
    Explanations

    references to graphical user interface elements and color specifications

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

    colors and GTK

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    းက
    -0.37
     salmón
    -0.36
     resisted
    -0.36
     ajud
    -0.34
     inneces
    -0.34
     iné
    -0.34
     lauf
    -0.34
    ediakan
    -0.33
     Aprove
    -0.33
    Reprodução
    -0.33
    POSITIVE LOGITS
     Colors
    2.20
    Colors
    1.78
     Colours
    1.59
     COLORS
    1.58
     colors
    1.51
    colors
    1.41
    Colours
    1.34
    COLORS
    1.29
     colours
    1.25
    colours
    1.16
    Act Density 0.001%

    No Known Activations