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

    Neuronpedia

    INDEX
    Explanations

    Python type hints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হোমিওপ্যাথ
    0.43
    Answers
    0.43
     %@
    0.42
    عتها
    0.41
    Double
    0.40
    ூரில்
    0.40
    DOUBLE
    0.39
    厚的
    0.39
     doubled
    0.39
     Reef
    0.39
    POSITIVE LOGITS
     str
    0.95
    str
    0.84
     dict
    0.69
     Union
    0.68
     tuple
    0.68
     None
    0.61
     int
    0.59
    None
    0.56
     typing
    0.56
    Union
    0.56
    Act Density 0.040%

    No Known Activations