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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     wom
    0.82
    %
    0.82
     ڪ
    0.80
    ributive
    0.78
    आय
    0.75
     assort
    0.74
     ष
    0.73
    ने
    0.72
    Лю
    0.70
    .*
    0.70
    POSITIVE LOGITS
     laughing
    1.17
    شار
    1.04
    hull
    1.03
    schutz
    1.01
     Habsburg
    1.01
    oL
    1.00
     nails
    1.00
     laughter
    1.00
     ENC
    0.99
    hlas
    0.98
    Act Density 0.000%

    No Known Activations