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

    Neuronpedia

    INDEX
    Explanations

    treated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è¿Ļåľº
    -0.33
    åįĬ天
    -0.32
    éĤ£å¤©
    -0.32
    åĩºå¸Ńä¼ļè®®
    -0.30
    çĶŁæĹ¥
    -0.30
    åıĤåĬłä¼ļè®®
    -0.29
    è¿Ļ次
    -0.28
    ä¸Ģåľº
    -0.28
    åºĨç¥Ŀ
    -0.28
    åıĤä¼ļ
    -0.28
    POSITIVE LOGITS
    æ¯ıåij¨
    0.44
     daily
    0.39
    æ¯ı天
    0.39
    æ¯ıæĹ¥
    0.35
     weekly
    0.35
     nightly
    0.34
    æĹ¥å¸¸çĶŁæ´»
    0.34
    daily
    0.33
    åĩºåħ¥
    0.33
    æĹ¥å¸¸
    0.32
    Act Density 0.001%

    No Known Activations