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

    Neuronpedia

    INDEX
    Explanations

    Semaphore

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of semaphores (i.e. the word “semaphore” and its fragments), indicating synchronization constructs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Fakült
    -0.07
    _locals
    -0.07
     gridColumn
    -0.07
     жар
    -0.07
    .ArrayAdapter
    -0.07
    .metric
    -0.06
    (:,
    -0.06
    局
    -0.06
     konu
    -0.06
     createdAt
    -0.06
    POSITIVE LOGITS
     Semaphore
    0.07
     semaphore
    0.07
     сопров
    0.07
    οι
    0.06
     Human
    0.06
    suppress
    0.06
    았
    0.06
     exclus
    0.06
     sergeant
    0.06
    soles
    0.06
    Act Density 0.003%

    No Known Activations