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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     silahkan
    0.93
    ைகோ
    0.91
    orius
    0.86
     correr
    0.85
     unimagin
    0.85
    ori
    0.85
     به
    0.85
     jij
    0.84
     allé
    0.82
     കു
    0.82
    POSITIVE LOGITS
     legislate
    0.99
     Elevations
    0.97
    గ
    0.96
    ]|
    0.96
     sexes
    0.94
    ]}$
    0.93
    ֙
    0.93
     թվական
    0.92
    Prevention
    0.92
    methylation
    0.92
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.