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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    The neuron detects quoted names or titles—proper‐noun phrases and event/program/book/movie titles enclosed in quotation marks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /ayushman
    -0.06
    ='"
    -0.06
     getRandom
    -0.06
     HOL
    -0.06
    orizontal
    -0.06
     CPUs
    -0.06
    Red
    -0.06
    beb
    -0.06
    Usu
    -0.05
     recreational
    -0.05
    POSITIVE LOGITS
    家族
    0.08
    0.07
    Closing
    0.07
    헌
    0.07
     
    0.07
     thanking
    0.07
     ozone
    0.07
     localized
    0.07
    しの
    0.06
    σκευ
    0.06
    Act Density 0.072%

    No Known Activations