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

    Neuronpedia

    INDEX
    Explanations

    C++ namespaces and classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    typedef
    0.48
     typedef
    0.46
     sizeof
    0.43
     mastering
    0.40
    ioctl
    0.39
     associativity
    0.39
     scanf
    0.39
     fflush
    0.38
     ty
    0.38
     customPlot
    0.38
    POSITIVE LOGITS
    namespace
    0.68
     namespace
    0.51
     USING
    0.49
    USING
    0.47
     usando
    0.44
    NAMESPACE
    0.43
    лимп
    0.41
     utilizando
    0.40
     utilizzando
    0.39
     зовніш
    0.39
    Act Density 0.009%

    No Known Activations