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

    Neuronpedia

    INDEX
    Explanations

    , otherwise use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ানির
    0.43
    改装
    0.42
    俄
    0.42
    大学
    0.41
    天赋
    0.40
     TRANSP
    0.40
    户
    0.39
    ADDING
    0.39
     ক্ষমতা
    0.38
     COLLEGE
    0.38
    POSITIVE LOGITS
     only
    0.62
     толькі
    0.50
    only
    0.45
     fray
    0.44
     Menon
    0.43
     them
    0.42
     unworthy
    0.41
     alleen
    0.41
     Only
    0.41
     seulement
    0.41
    Act Density 0.002%

    No Known Activations