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

    Neuronpedia

    INDEX
    Explanations

    research and explaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ontwerp
    0.48
     doxy
    0.48
     inférieur
    0.46
     Crimea
    0.43
     بالټ
    0.43
     провер
    0.42
     colitis
    0.42
     heparin
    0.42
     cuero
    0.41
    Compras
    0.41
    POSITIVE LOGITS
    to
    0.44
    と呼ばれる
    0.41
    ukawa
    0.39
    载
    0.38
    unsaturated
    0.38
    tou
    0.38
    always
    0.38
    ‌آ
    0.38
    coordinated
    0.37
    H
    0.37
    Act Density 0.016%

    No Known Activations