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

    Neuronpedia

    INDEX
    Explanations

    mentions of colors, especially when used to describe something, and the word "in"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bish
    -0.07
    rone
    -0.07
    htdocs
    -0.07
    Ñıн
    -0.06
    azon
    -0.06
    zej
    -0.06
    berger
    -0.06
    нова
    -0.06
     Giang
    -0.06
    eyh
    -0.06
    POSITIVE LOGITS
     sizes
    0.10
     variety
    0.10
     options
    0.09
     flavors
    0.09
     colors
    0.08
    .available
    0.07
     varieties
    0.07
     shapes
    0.07
     range
    0.07
     option
    0.07
    Act Density 0.019%

    No Known Activations