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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ;
    0.95
    しまう
    0.94
    able
    0.93
    ous
    0.93
    おります
    0.93
    ive
    0.93
    )?
    0.91
    )]
    0.90
    ower
    0.89
    ):
    0.89
    POSITIVE LOGITS
     outliers
    1.20
     przedsi
    1.14
    ি
    1.07
     domani
    1.06
     serán
    1.05
    ни
    1.05
     biopsies
    1.04
     habitaciones
    1.02
     outlier
    1.02
    लियों
    1.02
    Act Density 0.000%

    No Known Activations