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

    Neuronpedia

    INDEX
    Explanations

    digits, numbers, and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     टिक
    0.41
    アレ
    0.41
     hypocrisy
    0.40
     plaus
    0.39
    ovanie
    0.39
    తో
    0.38
    ленность
    0.38
     لوگ
    0.38
     solvable
    0.38
    કી
    0.37
    POSITIVE LOGITS
     程序
    0.46
     Neph
    0.43
     उपहार
    0.43
    arithmic
    0.42
     Relatively
    0.42
    “(
    0.41
     Yunnan
    0.41
     രണ്ടു
    0.41
     RMB
    0.41
     ۹
    0.40
    Act Density 0.011%

    No Known Activations