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

    Neuronpedia

    INDEX
    Explanations

    am an AI Chatbot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的标准
    0.79
    Standard
    0.71
     Unusual
    0.70
     peer
    0.70
     standard
    0.69
    ronic
    0.69
     helpers
    0.69
     необы
    0.68
    かせ
    0.68
     unusual
    0.67
    POSITIVE LOGITS
    នុ
    0.73
     promulgating
    0.70
     फक्त
    0.69
     mandates
    0.69
    aży
    0.68
     vidhan
    0.68
     focussing
    0.67
     melakukan
    0.67
    嬲
    0.66
     equipments
    0.66
    Act Density 0.021%

    No Known Activations