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

    Neuronpedia

    INDEX
    Explanations

    user experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шин
    -0.08
     christ
    -0.08
    istrik
    -0.08
     verklar
    -0.08
     Punt
    -0.07
    UTILITY
    -0.07
     смер
    -0.07
    loor
    -0.07
    dag
    -0.07
     RECT
    -0.07
    POSITIVE LOGITS
    体验
    0.17
     Erlebnis
    0.11
     trải
    0.11
     अनुभव
    0.11
     erleben
    0.10
     experience
    0.10
     تجربه
    0.09
     experiencias
    0.09
     experiences
    0.09
     અનુભવ
    0.09
    Act Density 0.046%

    No Known Activations