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

    Neuronpedia

    INDEX
    Explanations

    The Shining

    np_max-act · gemini-2.0-flash

    This neuron activates on subword pieces of the film title “Shining,” effectively spotting mentions of “The Shining.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Nurs
    -0.06
    �
    -0.06
     alınması
    -0.06
     masks
    -0.06
    讨
    -0.06
     pytest
    -0.06
    ewidth
    -0.06
     adulti
    -0.06
    주시
    -0.06
    (passport
    -0.06
    POSITIVE LOGITS
     (!((
    0.07
     discrepancies
    0.06
     energy
    0.06
     sitcom
    0.06
     outnumber
    0.06
    reative
    0.06
     сбор
    0.06
     smoothly
    0.06
     through
    0.06
     обы
    0.06
    Act Density 0.002%

    No Known Activations