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

    Neuronpedia

    INDEX
    Explanations

    python os module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مقام
    0.39
     sớm
    0.38
     सेकेंडरी
    0.38
    轅
    0.37
    Things
    0.37
    高兴
    0.37
     realised
    0.37
    ባቢ
    0.37
    cX
    0.37
    acharya
    0.36
    POSITIVE LOGITS
     Os
    0.88
     OS
    0.84
     os
    0.69
    OS
    0.64
     Ос
    0.64
    Os
    0.64
     Osm
    0.64
     Osc
    0.64
     OSM
    0.62
     ос
    0.60
    Act Density 0.014%

    No Known Activations