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

    Neuronpedia

    INDEX
    Explanations

    items():

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    udp
    0.49
    abu
    0.49
     শিক্ষার
    0.46
    PagerAdapter
    0.46
    规范
    0.45
    代引
    0.45
    糇
    0.44
     бло
    0.43
    ματο
    0.43
    រ
    0.43
    POSITIVE LOGITS
    א
    0.63
     |
    0.61
     illuminated
    0.56
     $
    0.55
     ۵
    0.55
     look
    0.54
     aerodynamic
    0.54
     optical
    0.53
     riveting
    0.53
     curated
    0.53
    Act Density 0.001%

    No Known Activations