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

    Neuronpedia

    INDEX
    Explanations

    machine code or settling dust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不会
    0.47
    <0xB7>
    0.45
    我
    0.43
    Би
    0.40
    齜
    0.40
    自动
    0.40
    Declare
    0.39
     később
    0.39
    Access
    0.39
    芈
    0.39
    POSITIVE LOGITS
     pover
    0.47
     finite
    0.46
     leisurely
    0.46
     મળ
    0.45
     forn
    0.45
     durg
    0.44
     sump
    0.44
     pigmented
    0.44
    neet
    0.43
     rinsing
    0.43
    Act Density 0.003%

    No Known Activations