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

    Neuronpedia

    INDEX
    Explanations

    except Exception as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     危
    0.48
    筲
    0.46
    તી
    0.46
     gebruiken
    0.46
     ຮ
    0.45
     gunakan
    0.45
    絓
    0.45
    ভূমিতে
    0.44
    䊂
    0.44
     เห็น
    0.44
    POSITIVE LOGITS
    (
    0.49
    Exception
    0.48
     exceptions
    0.47
     Exception
    0.44
     any
    0.44
     infections
    0.43
     timeouts
    0.42
     exorbitant
    0.40
     unexpected
    0.39
     discomfort
    0.39
    Act Density 0.052%

    No Known Activations