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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     vezes
    1.03
     espécie
    0.95
     interesse
    0.87
    fotos
    0.86
     conseguenza
    0.85
     empresas
    0.84
     tarifas
    0.84
    entingan
    0.84
     riform
    0.82
     direita
    0.81
    POSITIVE LOGITS
    你
    0.75
    </tr>
    0.73
    ED
    0.71
    ης
    0.70
    你会
    0.70
     incubator
    0.67
     investigation
    0.64
    RE
    0.64
    其中
    0.64
     absorb
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.