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

    Neuronpedia

    INDEX
    Explanations

    Universidad

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens naming academic institutions or their components (e.g. “Universidade,” “Faculdade,” “Instituto”), i.e. university and research‐institute affiliation terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     consumer
    -0.07
    Config
    -0.07
    target
    -0.07
    DEFAULT
    -0.07
    allow
    -0.06
    missions
    -0.06
     data
    -0.06
    GROUP
    -0.06
    frame
    -0.06
     action
    -0.06
    POSITIVE LOGITS
    说话
    0.07
     стратег
    0.06
    огу
    0.06
     meslek
    0.06
     แบบ
    0.06
     or
    0.06
     předmět
    0.06
    ювання
    0.06
     Ск
    0.06
    \Entity
    0.06
    Act Density 0.016%

    No Known Activations