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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    onato
    -1.05
     dieną
    -1.04
     niebla
    -1.00
     accesible
    -0.99
     sega
    -0.99
     Caj
    -0.96
     frança
    -0.94
     troy
    -0.94
    Caj
    -0.94
     سامسون
    -0.93
    POSITIVE LOGITS
    .
    0.99
     also
    0.97
     but
    0.93
     tazas
    0.86
     dirección
    0.84
     凉
    0.83
    isContained
    0.83
     hozz
    0.82
     navideñas
    0.82
    证券
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.