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

    Neuronpedia

    INDEX
    Explanations

    legislative bodies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是
    0.60
    ۔
    0.56
    .
    0.49
    सी
    0.48
    ‌ای
    0.47
    ።
    0.46
    b
    0.45
    は
    0.45
     первым
    0.43
    는
    0.41
    POSITIVE LOGITS
     amenities
    0.43
    し
    0.43
     impotence
    0.41
     financi
    0.41
    αν
    0.40
    لې
    0.40
     hvad
    0.40
     leistungs
    0.40
     sabbatical
    0.39
     almighty
    0.39
    Act Density 0.000%

    No Known Activations