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

    Neuronpedia

    INDEX
    Explanations

    instances of collaborative activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    we discussing topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.67
     RoutedEventArgs
    -0.67
    -0.62
    RectangleBorder
    -0.61
    gridx
    -0.54
    ########.
    -0.53
    MLLoader
    -0.53
    XmlAccessorType
    -0.50
     rowspan
    -0.49
    __':
    -0.48
    POSITIVE LOGITS
     discussion
    0.67
     excursions
    0.64
    Activities
    0.62
     discussions
    0.60
     indoors
    0.60
     we
    0.60
     discussing
    0.60
     emphasis
    0.60
     discussed
    0.59
     topics
    0.59
    Act Density 0.162%

    No Known Activations