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

    Neuronpedia

    INDEX
    Explanations

    java programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estrut
    0.89
     status
    0.85
    fasc
    0.82
    σκεται
    0.80
     மூலம்
    0.79
    Gender
    0.79
    حاء
    0.78
     Status
    0.78
     situado
    0.77
    ндагы
    0.77
    POSITIVE LOGITS
     fallback
    1.22
     tinker
    1.14
    Ny
    1.04
    每次
    1.03
    ToRemove
    1.03
    پن
    1.03
    允许
    1.02
     Percolation
    1.02
     coughing
    1.02
    蚂
    1.02
    Act Density 0.015%

    No Known Activations