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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ίνει
    0.94
    ين
    0.87
    ı
    0.86
    iduciary
    0.81
    吸引
    0.80
    ion
    0.80
    ів
    0.80
    ai
    0.79
     montré
    0.79
    1
    0.78
    POSITIVE LOGITS
    ри
    1.18
     waged
    1.07
     brachial
    1.04
    чкой
    1.02
     touchdowns
    1.01
     supersymmetry
    1.01
     Yatha
    1.00
     fundamentos
    1.00
    ỡi
    0.99
    𝖽
    0.97
    Act Density 0.000%

    No Known Activations