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

    Neuronpedia

    INDEX
    Explanations

    legislation governing laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    श
    2.09
    이자
    2.05
    ა
    2.03
    تان
    2.02
    з
    1.93
    мп
    1.84
    л
    1.84
    ंग
    1.83
    で
    1.77
    ्टी
    1.76
    POSITIVE LOGITS
    ни
    2.30
    ut
    2.27
    islation
    1.98
    is
    1.93
    id
    1.90
    it
    1.83
    are
    1.81
    <0x80>
    1.77
    носит
    1.74
     demikian
    1.72
    Act Density 0.001%

    No Known Activations