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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lij
    1.08
     Х
    1.00
    логи
    0.93
    Х
    0.92
     carro
    0.90
     Verd
    0.90
     দুজনের
    0.88
    lend
    0.88
     strumenti
    0.88
    oree
    0.88
    POSITIVE LOGITS
    ՞
    0.92
    ུ་
    0.89
     faulted
    0.83
    us
    0.83
    WUE
    0.82
    ("-
    0.82
     "="
    0.80
     "|"
    0.79
     "-"
    0.78
    gun
    0.77
    Act Density 0.000%

    No Known Activations