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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     אבל
    1.06
     sortBy
    1.06
     Adapun
    1.04
     MIMO
    1.00
     chops
    1.00
     Although
    1.00
     וא
    1.00
    पाउंड
    0.99
     Means
    0.98
     समानार्थी
    0.95
    POSITIVE LOGITS
    tiles
    1.14
    tok
    1.09
     kuul
    1.06
    tamb
    0.94
     castillo
    0.91
    ेक्षित
    0.91
    iid
    0.90
    ត
    0.90
     рождения
    0.89
     Jocelyn
    0.88
    Act Density 0.000%

    No Known Activations