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

    Neuronpedia

    INDEX
    Explanations

    upper

    np_max-act · gemini-2.0-flash

    This neuron detects uses of the word “upper” in descriptions of anatomical tracts or body regions (e.g. “upper respiratory tract,” “upper airways,” “upper gastrointestinal”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    wife
    -0.07
     براى
    -0.06
    뉴스
    -0.06
    Na
    -0.06
     snowy
    -0.06
    アルバ
    -0.06
     кле
    -0.06
    Τα
    -0.06
    роничес
    -0.06
     INS
    -0.06
    POSITIVE LOGITS
    berries
    0.08
     instructed
    0.07
    .metric
    0.07
    ('.'
    0.07
     changes
    0.06
    \widgets
    0.06
    」「
    0.06
     Assuming
    0.06
     change
    0.06
     succeed
    0.06
    Act Density 0.003%

    No Known Activations