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

    Neuronpedia

    INDEX
    Explanations

    American Indian themes

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect references to specific Native American names, terms, and cultural events (e.g. tribal figures like Sitting Bull or Crazy Horse and events like powwows).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     infertility
    -0.06
    /AFP
    -0.06
    ondon
    -0.06
    gst
    -0.06
    motor
    -0.06
     getClient
    -0.06
    στ
    -0.06
    .Call
    -0.06
    Detector
    -0.06
     бл
    -0.06
    POSITIVE LOGITS
     =======
    0.07
     PAS
    0.06
     streamlined
    0.06
     Yok
    0.06
     etmek
    0.06
    .publisher
    0.06
     hod
    0.06
     poi
    0.06
    empor
    0.06
     през
    0.06
    Act Density 0.049%

    No Known Activations