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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ago
    1.00
     نوم
    0.96
     daw
    0.96
     mát
    0.93
     weeks
    0.92
     数
    0.92
     води
    0.91
     daj
    0.90
     Coming
    0.89
    ks
    0.89
    POSITIVE LOGITS
    erase
    1.23
    蒾
    1.09
    sels
    1.05
     thaliana
    1.04
    eyJ
    1.03
     studierte
    1.01
     begren
    1.01
     ovako
    1.01
    чення
    1.00
     neuest
    0.99
    Act Density 0.086%

    No Known Activations