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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ار
    1.00
     Humanities
    0.96
    匚
    0.96
     Fruit
    0.92
     Family
    0.91
     Prisma
    0.91
     Network
    0.91
     Basics
    0.90
     Parque
    0.90
     Galaxies
    0.90
    POSITIVE LOGITS
     tắt
    0.98
    garakan
    0.83
     ξ
    0.81
    ы
    0.80
    énergie
    0.79
    soever
    0.79
     топлива
    0.79
    энер
    0.77
     tần
    0.76
    ární
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.