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

    Neuronpedia

    INDEX
    Explanations

    will enable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    re
    0.48
     மட்டுமே
    0.47
     didn
    0.46
    ia
    0.46
     D
    0.45
    killed
    0.45
    inqu
    0.44
    dy
    0.44
    ir
    0.43
     Gand
    0.43
    POSITIVE LOGITS
     ovlád
    0.48
     المدرسة
    0.48
    że
    0.46
     аспек
    0.46
     이러한
    0.44
    MovieDetails
    0.43
     Баскетбол
    0.43
     这些
    0.43
     głów
    0.43
     berücksichtigt
    0.43
    Act Density 0.007%

    No Known Activations