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

    Neuronpedia

    INDEX
    Explanations

    using namespace std

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ROBERT
    0.42
    Robert
    0.39
    logged
    0.39
    cett
    0.38
    ackbar
    0.37
    शियम
    0.37
     रॉबर्ट
    0.37
    心を
    0.37
    steacher
    0.37
     outwards
    0.37
    POSITIVE LOGITS
     namespace
    0.92
    namespace
    0.52
    Namespace
    0.51
     std
    0.45
     Namespace
    0.45
     namespaces
    0.44
    ಬಿ
    0.41
     standar
    0.39
     enum
    0.39
     integers
    0.38
    Act Density 0.002%

    No Known Activations