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

    Neuronpedia

    INDEX
    Explanations

    other countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    非常
    0.54
    5
    0.53
    ore
    0.51
    ৫
    0.51
    owers
    0.50
    4
    0.50
    あまり
    0.50
    ২৯
    0.49
    -
    0.48
    ாதார
    0.47
    POSITIVE LOGITS
     skillset
    0.43
     ہوگئی
    0.42
     history
    0.41
     circumstance
    0.41
     tehdä
    0.41
     words
    0.40
     sentence
    0.40
     Hank
    0.40
     tät
    0.40
     gjøre
    0.40
    Act Density 0.096%

    No Known Activations