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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "colors"

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

    colors or colours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }
    -0.41
    assertArray
    -0.38
     game
    -0.37
     때
    -0.36
    <eos>
    -0.34
    })
    -0.34
     PLAN
    -0.34
    -
    -0.33
    p
    -0.33
    ]
    -0.33
    POSITIVE LOGITS
    colors
    2.58
    Colors
    2.13
    COLORS
    1.85
    colours
    1.84
     Colors
    1.78
     COLORS
    1.70
     Colours
    1.62
    Colours
    1.58
     colors
    1.57
     colours
    1.46
    Act Density 0.001%

    No Known Activations