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

    Neuronpedia

    INDEX
    Explanations

    references and citations

    np_max-act · gemini-2.0-flash

    The neuron activates on author surname tokens in bibliographic citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Aure
    -0.06
     giveaway
    -0.06
     αυτά
    -0.06
     Spike
    -0.06
     แ
    -0.06
     Africa
    -0.06
     Bernard
    -0.06
     Kernel
    -0.06
     cameras
    -0.06
     foreground
    -0.06
    POSITIVE LOGITS
    14
    0.07
    icipant
    0.06
    着
    0.06
    .cn
    0.06
    وزيع
    0.06
     nationalists
    0.06
     dad
    0.06
    095
    0.06
    лись
    0.06
     특별
    0.06
    Act Density 0.024%

    No Known Activations