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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on the coordinating conjunction “or.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     flight
    -0.07
     bounding
    -0.06
    عان
    -0.06
    -service
    -0.06
    _manual
    -0.06
    975
    -0.06
    _main
    -0.06
    Play
    -0.06
    _Class
    -0.06
     orchest
    -0.06
    POSITIVE LOGITS
     olumsuz
    0.08
    (U
    0.07
    ớp
    0.07
     изб
    0.07
     outage
    0.07
    _IL
    0.06
     Huckabee
    0.06
    .Im
    0.06
    .spring
    0.06
     vòng
    0.06
    Act Density 0.043%

    No Known Activations