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

    Neuronpedia

    INDEX
    Explanations

    CSS and color-related properties and their values

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

    Colors, especially red and blue

    np_acts-logits-general · gemini-2.0-flash

    red and color properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.72
    RenderAtEndOf
    -0.61
     }}"></
    -0.57
    klass
    -0.51
    ?}",
    -0.51
     CascadeType
    -0.50
    binant
    -0.50
    
    -0.49
    utilisons
    -0.47
    Referencer
    -0.47
    POSITIVE LOGITS
     lighten
    0.90
     lighter
    0.79
     lightest
    0.78
     darkest
    0.77
     transparency
    0.76
     transpa
    0.76
     darken
    0.76
     opacity
    0.75
     brightened
    0.72
     brighter
    0.72
    Act Density 0.061%

    No Known Activations