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

    Neuronpedia

    INDEX
    Explanations

    how to execute operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    墙
    0.43
    ﮧ
    0.43
    灯
    0.42
    手机
    0.42
    ếc
    0.42
    板
    0.41
    餐厅
    0.41
    等の
    0.41
    电脑
    0.40
    锁
    0.40
    POSITIVE LOGITS
     furthermore
    0.54
     moreover
    0.52
     imperatives
    0.51
    並且
    0.50
    Furthermore
    0.46
     Furthermore
    0.45
    并且
    0.43
    Moreover
    0.43
     tractable
    0.42
     forthwith
    0.41
    Act Density 0.001%

    No Known Activations