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

    Neuronpedia

    INDEX
    Explanations

    references to scientific and technical terms or concepts

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

    colors

    np_acts-logits-general · gemini-2.0-flash

    colors and descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nodoc
    -0.52
    forChild
    -0.47
     htons
    -0.45
    μφωνα
    -0.43
     seismo
    -0.42
     betrug
    -0.41
    toFixed
    -0.39
     Söz
    -0.39
     الحره
    -0.39
    olahan
    -0.39
    POSITIVE LOGITS
     color
    2.23
     colour
    2.07
     colors
    2.05
     colored
    2.00
     blue
    1.99
     yellow
    1.97
     colours
    1.91
     purple
    1.90
     coloured
    1.89
    color
    1.83
    Act Density 1.238%

    No Known Activations