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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ist
    0.78
    a
    0.76
    g
    0.70
    र्
    0.70
    ning
    0.70
    sapp
    0.70
     registration
    0.70
     threw
    0.68
     sliding
    0.67
    ig
    0.65
    POSITIVE LOGITS
     принад
    0.84
     Кы
    0.82
    ровень
    0.80
     ámbitos
    0.71
     aberrations
    0.71
    которы
    0.71
     Большая
    0.71
    Ẩ
    0.70
     самый
    0.69
    ystem
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.