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

    Neuronpedia

    INDEX
    Explanations

    Artwork/creation

    np_max-act · gemini-2.0-flash

    This neuron activates on attribution phrases that credit who made or illustrated the artwork (e.g. “created by,” “illustrated by,” “done by,” etc.).

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

    references to culinary experiences and food-related concepts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    LE
    -0.08
     shutter
    -0.07
    hci
    -0.07
    _catalog
    -0.07
     Dust
    -0.07
    ليات
    -0.07
    -cons
    -0.06
     yếu
    -0.06
    .Lib
    -0.06
    .Result
    -0.06
    POSITIVE LOGITS
    ]]></
    0.07
    ':''
    0.06
     années
    0.06
     manus
    0.06
     antenna
    0.06
    .ReadInt
    0.06
     Angola
    0.06
    isOpen
    0.06
    jug
    0.06
     шту
    0.06
    Act Density 0.039%

    No Known Activations