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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ＰＥＮＡＮＡ
    1.12
     veze
    1.06
    ecommerce
    1.06
     verge
    1.03
     elétrica
    1.00
    ésil
    1.00
     tacked
    0.99
    uert
    0.99
    puff
    0.99
     oferece
    0.99
    POSITIVE LOGITS
    H
    0.83
     di
    0.82
     pound
    0.79
    begin
    0.76
    淋
    0.75
    let
    0.75
    出発
    0.75
     মাই
    0.74
     philosopher
    0.74
    哲学
    0.73
    Act Density 0.000%

    No Known Activations