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

    Neuronpedia

    INDEX
    Explanations

    real, float, or double types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     double
    0.90
    double
    0.82
     Double
    0.81
    Double
    0.79
    ("%.
    0.71
     DOUBLE
    0.71
     двой
    0.66
    round
    0.65
     {:.
    0.64
     डबल
    0.63
    POSITIVE LOGITS
     निरा
    0.43
     радика
    0.39
     منه
    0.39
     Appendix
    0.39
     chiều
    0.39
    瘡
    0.38
     cah
    0.38
    Opera
    0.38
    NUS
    0.38
     NUS
    0.37
    Act Density 0.027%

    No Known Activations