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

    Neuronpedia

    INDEX
    Explanations

    difference between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innumerable
    0.77
     yoktur
    0.66
    有很多
    0.65
    常に
    0.63
     meines
    0.63
    たくさん
    0.61
    每一
    0.61
    私の
    0.60
     యొక్క
    0.60
     моей
    0.60
    POSITIVE LOGITS
     mereka
    1.16
     তারাও
    1.10
     they
    1.07
     ebenfalls
    1.07
     alerting
    1.06
    他们
    1.04
     alerted
    1.03
    他們
    1.02
    他也
    1.02
     তিনিও
    1.01
    Act Density 0.001%

    No Known Activations