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

    Neuronpedia

    INDEX
    Explanations

    color definitions in code

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

    colors

    np_acts-logits-general · gemini-2.0-flash

    programmatic color definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ionado
    -0.54
     getItemCount
    -0.50
    WindowSize
    -0.49
     GenerationType
    -0.49
    illotine
    -0.48
    actylus
    -0.47
     Leaf
    -0.47
    almo
    -0.47
     silent
    -0.46
    Leaf
    -0.46
    POSITIVE LOGITS
     colors
    1.12
     color
    1.03
     Colors
    1.03
     colours
    0.92
     colored
    0.90
     COLOR
    0.90
     Color
    0.89
     COLORS
    0.89
    Color
    0.88
     couleur
    0.88
    Act Density 0.155%

    No Known Activations