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

    Neuronpedia

    INDEX
    Explanations

    history and heritage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Subscribers
    0.66
    鹑
    0.63
    َوْ
    0.62
    Behavior
    0.61
     Subscriber
    0.61
     verurs
    0.60
     नसल्या
    0.59
    اتف
    0.59
     বিনা
    0.58
    endra
    0.58
    POSITIVE LOGITS
     history
    3.08
    history
    2.73
     History
    2.68
     heritage
    2.67
    History
    2.65
     histories
    2.64
     historical
    2.63
    历史
    2.60
    歷史
    2.57
     historia
    2.47
    Act Density 1.031%

    No Known Activations