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

    Neuronpedia

    INDEX
    Explanations

    moral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Faces
    -0.08
    igere
    -0.08
     специалисты
    -0.08
     giga
    -0.08
     фирмы
    -0.08
     faszin
    -0.08
     mün
    -0.08
    Collider
    -0.08
     кожи
    -0.08
     бетон
    -0.08
    POSITIVE LOGITS
    寓
    0.11
     lesson
    0.09
    道
    0.09
     قصة
    0.09
     morals
    0.08
    教育
    0.08
    lesson
    0.08
     कहानी
    0.08
     Vietnamese
    0.08
     कथा
    0.08
    Act Density 0.018%

    No Known Activations