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

    Neuronpedia

    INDEX
    Explanations

    critical analysis of trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    测试
    0.57
    ทด
    0.54
    实验
    0.51
    测
    0.49
     ทด
    0.48
    计算
    0.48
     intuition
    0.47
     experiment
    0.47
     اختبار
    0.46
     测试
    0.46
    POSITIVE LOGITS
     reviews
    0.52
    进展
    0.51
     Trends
    0.49
     REVIEW
    0.49
     summarizes
    0.49
    近年
    0.49
    literature
    0.48
     littérature
    0.47
    progress
    0.47
     progrès
    0.47
    Act Density 0.151%

    No Known Activations