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

    Neuronpedia

    INDEX
    Explanations

    listing challenges and difficulties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或者是
    0.49
    Enum
    0.46
     unspecified
    0.44
     generalizing
    0.41
    我会
    0.41
    З
    0.40
    Somewhere
    0.39
     +"
    0.38
     straightforward
    0.38
    SubType
    0.38
    POSITIVE LOGITS
     famously
    0.98
     infamous
    0.85
     notorious
    0.72
     terkenal
    0.71
     famed
    0.71
     অদ্ভুত
    0.68
     प्रसिद्ध
    0.66
     عجیب
    0.66
     कथित
    0.63
     eponymous
    0.63
    Act Density 0.659%

    No Known Activations