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

    Neuronpedia

    INDEX
    Explanations

    synonyms and translations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    manız
    0.29
    这个
    0.28
    9
    0.28
    4
    0.26
    8
    0.26
    たちは
    0.25
    ленные
    0.25
    したのは
    0.24
    6
    0.24
    それが
    0.23
    POSITIVE LOGITS
     ebenfalls
    0.49
     ibid
    0.39
     ਵੀ
    0.36
     أيضا
    0.35
     tiež
    0.34
     επίσης
    0.34
    ibid
    0.33
     likewise
    0.33
     opět
    0.33
     također
    0.32
    Act Density 0.641%

    No Known Activations