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

    Neuronpedia

    INDEX
    Explanations

    Art descriptions

    np_max-act · gemini-2.0-flash

    The neuron flags the kinds of tokens you see in an artwork’s infobox—titles, artist names, mediums (e.g. “oil on panel,” “graphite on paper”), dimensions, and classification labels like “landscape” or “portrait.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    mentions of specific artists and their works.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .imp
    -0.07
    .COLUMN
    -0.07
    :Number
    -0.06
     Sofia
    -0.06
     smrti
    -0.06
    (Int
    -0.06
     translator
    -0.06
    _icon
    -0.06
    息
    -0.06
     gardens
    -0.06
    POSITIVE LOGITS
     prizes
    0.06
    uras
    0.06
     �
    0.06
    _resource
    0.06
     mbedtls
    0.06
    ativa
    0.06
     cush
    0.06
     Maximum
    0.06
     관련
    0.05
     Profiles
    0.05
    Act Density 0.005%

    No Known Activations