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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    י
    1.08
    <0xAB>
    1.01
    a
    1.00
    c
    1.00
    い
    0.98
    (
    0.89
    й
    0.87
    ć
    0.86
    ت
    0.85
    ل
    0.85
    POSITIVE LOGITS
     montre
    1.13
     narrator
    1.03
    summar
    1.03
     junio
    1.02
     faktor
    1.01
    democratic
    1.01
     ekst
    0.97
     मोहब्बत
    0.96
     lampe
    0.96
     azar
    0.95
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.