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

    Neuronpedia

    INDEX
    Explanations

    He

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on the sentence-initial third-person male pronoun “He.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Where
    -0.07
    线
    -0.06
     referral
    -0.06
    دیگر
    -0.06
     карти
    -0.06
    λιο
    -0.06
    enary
    -0.06
     samot
    -0.06
    (Create
    -0.06
     büny
    -0.06
    POSITIVE LOGITS
     wrestler
    0.07
     kiss
    0.07
     Eag
    0.06
    [@
    0.06
    //{↵
    0.06
     Headquarters
    0.06
    Marketing
    0.06
    년에는
    0.06
     участ
    0.06
    θμ
    0.06
    Act Density 0.032%

    No Known Activations