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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     assault
    0.82
    ваты
    0.79
     объяс
    0.71
    󠁢
    0.71
     runny
    0.70
    zeiten
    0.70
     Assault
    0.69
     प्रेर
    0.68
     assaults
    0.67
     meditations
    0.66
    POSITIVE LOGITS
     що
    1.02
     Що
    0.88
    가의
    0.87
     până
    0.81
    ৫
    0.78
     khắp
    0.78
     that
    0.76
     Une
    0.75
     hingga
    0.75
    volving
    0.74
    Act Density 0.000%

    No Known Activations