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

    Neuronpedia

    INDEX
    Explanations

    Russian text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leik
    -0.08
     clair
    -0.08
     Actors
    -0.08
     shocks
    -0.07
     Patrick
    -0.07
     Clair
    -0.07
     ileti
    -0.07
     calm
    -0.07
     пройти
    -0.07
     ல
    -0.07
    POSITIVE LOGITS
     engross
    0.10
     perhatian
    0.09
     Aufmerksamkeit
    0.09
     কাজে
    0.08
     Concentr
    0.08
    يب
    0.08
    อยู่
    0.08
     concentración
    0.07
    想着
    0.07
     concentration
    0.07
    Act Density 0.018%

    No Known Activations