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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     impedir
    0.89
     cambios
    0.88
    ﺮ
    0.87
    DialogWhenLarge
    0.84
    ষুধ
    0.84
     Mannes
    0.83
     aislamiento
    0.83
     necesitar
    0.82
    々は
    0.82
     Mujer
    0.81
    POSITIVE LOGITS
    ’
    0.89
    >
    0.82
    Ї
    0.73
    '
    0.71
    ]
    0.71
     perché
    0.70
    ką
    0.67
     favorite
    0.66
     recognized
    0.65
    chat
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.