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

    Neuronpedia

    INDEX
    Explanations

    Demon Slayer, Demonologist, demo, demographics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HOA
    0.44
    ിക്കു
    0.43
    p
    0.42
    ा
    0.42
     HEK
    0.41
    pone
    0.40
     PR
    0.39
     PI
    0.39
     ].
    0.39
     nawet
    0.38
    POSITIVE LOGITS
     демо
    0.86
    Demon
    0.77
    Dem
    0.75
    demon
    0.75
    dem
    0.74
    DEM
    0.74
     Dem
    0.73
     डेमो
    0.73
    Демо
    0.71
    demos
    0.70
    Act Density 0.017%

    No Known Activations