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

    Neuronpedia

    INDEX
    Explanations

    medical conditions

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of specific NLP task names (e.g. sentiment analysis, named entity recognition, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ICollectionView
    -0.07
     Văn
    -0.07
    描
    -0.07
    скор
    -0.07
    مدة
    -0.06
    changed
    -0.06
    ớm
    -0.06
    (XML
    -0.06
     OD
    -0.06
     단
    -0.06
    POSITIVE LOGITS
    aktiv
    0.06
    QPushButton
    0.06
    bal
    0.06
    �
    0.06
    Chess
    0.06
     BG
    0.06
    0.05
     precedence
    0.05
     typedef
    0.05
     ‪
    0.05
    Act Density 0.178%

    No Known Activations