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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    di
    1.10
     t
    1.05
    bb
    1.04
     narrated
    1.03
    bf
    1.00
    ên
    0.99
    lu
    0.98
    grav
    0.97
    sp
    0.97
    dk
    0.96
    POSITIVE LOGITS
     vile
    1.00
     stave
    0.94
    ските
    0.92
    к
    0.91
    лав
    0.91
    ри
    0.90
     sanciones
    0.88
    मला
    0.88
     resultSet
    0.87
    ле
    0.87
    Act Density 0.000%

    No Known Activations