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

    Neuronpedia

    INDEX
    Explanations

    expert

    np_max-act · gemini-2.0-flash

    This neuron activates on words and phrases where the speaker states or defines their own role, expertise, or qualifications.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _dataset
    -0.07
     tablets
    -0.07
    theast
    -0.06
    Anna
    -0.06
    774
    -0.06
    Pri
    -0.06
     east
    -0.06
     CoreData
    -0.06
     Nova
    -0.06
     قرآن
    -0.06
    POSITIVE LOGITS
     абсолют
    0.07
    others
    0.06
    ,↵
    0.06
     fiercely
    0.06
    -trade
    0.06
       ↵
    0.06
     мови
    0.06
     Juni
    0.06
    ilebilir
    0.06
     plea
    0.06
    Act Density 0.021%

    No Known Activations