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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ع
    0.82
     specifica
    0.79
     physico
    0.78
    $).
    0.71
     intra
    0.70
     assertion
    0.70
    );
    0.68
     nucle
    0.68
     matrimon
    0.68
    )$
    0.67
    POSITIVE LOGITS
    с
    0.96
     nešto
    0.88
    ees
    0.86
    ee
    0.85
    iya
    0.85
    ၉
    0.82
    目光
    0.81
    ၈
    0.79
     Großbritannien
    0.78
     Б
    0.77
    Act Density 0.000%

    No Known Activations