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

    Neuronpedia

    INDEX
    Explanations

    ){

    np_max-act · gemini-2.0-flash

    discussions about public health and preventive measures related to illness.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on in-text structural reference cues—things like figure/table/section numbers, citation brackets, and related labels.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    inking
    -0.07
    968
    -0.06
    232
    -0.06
    vu
    -0.06
     filtering
    -0.06
     gün
    -0.06
     Col
    -0.06
    multiple
    -0.06
     Killing
    -0.06
    Death
    -0.06
    POSITIVE LOGITS
    (square
    0.07
    (entity
    0.07
    .writeValue
    0.06
     Lego
    0.06
    ?f
    0.06
     formidable
    0.06
     Incredible
    0.06
    (function
    0.06
     �
    0.06
    -share
    0.06
    Act Density 0.002%

    No Known Activations