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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Weight
    1.15
    Body
    1.04
    Feet
    1.04
    Celebrate
    1.03
    Rational
    1.02
    Arrange
    1.01
    Compare
    1.01
    Abort
    1.00
    Accuracy
    1.00
    Transactions
    0.99
    POSITIVE LOGITS
     \*
    1.02
     *
    0.94
     four
    0.89
     forty
    0.87
     ۴
    0.86
     */
    0.79
     *}
    0.79
     与
    0.78
     २०
    0.78
     cuatro
    0.77
    Act Density 0.000%

    No Known Activations