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

    Neuronpedia

    INDEX
    Explanations

    fake photos

    np_max-act · gemini-2.0-flash

    The neuron detects references to visual media or imagery (e.g. photos, videos, radiographs) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    onsense
    -0.07
    _accounts
    -0.07
    (remote
    -0.06
     içinde
    -0.06
    ukes
    -0.06
    AWS
    -0.06
    Audio
    -0.06
     sứ
    -0.06
     Biden
    -0.06
    Server
    -0.06
    POSITIVE LOGITS
    ellidos
    0.06
    _CUR
    0.06
    ???
    0.06
     guts
    0.06
    �
    0.06
     outnumber
    0.06
    нося
    0.06
    _CASE
    0.06
    @class
    0.06
    .NUM
    0.06
    Act Density 0.140%

    No Known Activations