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

    Neuronpedia

    INDEX
    Explanations

    letting, below, 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    щая
    0.86
    ೭
    0.86
     тях
    0.86
     বড়
    0.84
    asilkan
    0.84
    ө
    0.84
     врач
    0.81
     була
    0.80
     لدينا
    0.78
    yth
    0.77
    POSITIVE LOGITS
    ر
    0.86
     desl
    0.73
     Multiplayer
    0.71
     Stabil
    0.71
    AVES
    0.68
     Medi
    0.66
     auditions
    0.66
    d
    0.65
    ेंट
    0.65
     Techn
    0.64
    Act Density 0.001%

    No Known Activations