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

    Neuronpedia

    INDEX
    Explanations

    Mor, Fay, Petit, Pat, Mo, M

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.22
    á
    1.19
    л
    1.16
    。
    1.16
    in
    1.09
    se
    1.08
    q
    1.06
    t
    1.02
    ক
    1.02
    ग
    1.00
    POSITIVE LOGITS
    ри
    1.10
     υπάρχ
    1.05
     в
    1.01
     της
    0.90
     lords
    0.90
     μπορούν
    0.89
     centrifuged
    0.88
    larda
    0.87
     by
    0.86
    льну
    0.86
    Act Density 0.000%

    No Known Activations