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

    Neuronpedia

    INDEX
    Explanations

    making sense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Необходимо
    0.72
    ഭ്യാ
    0.72
     Elevation
    0.70
    нием
    0.68
    ပြု
    0.68
    állítás
    0.66
     மன்ற
    0.66
     Draw
    0.65
     مطم
    0.64
    им
    0.62
    POSITIVE LOGITS
     sense
    2.94
    sense
    2.45
     Sense
    2.42
    Sense
    2.17
     sentido
    2.17
     senso
    1.88
     senses
    1.79
     sens
    1.58
     sentidos
    1.54
     logical
    1.48
    Act Density 0.076%

    No Known Activations