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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     chở
    0.54
     financ
    0.52
     specializing
    0.52
     philanthrop
    0.52
     traffickers
    0.50
    ribusiness
    0.49
    अरविंद
    0.49
     guaranteeing
    0.48
     concomitant
    0.47
     🙏
    0.47
    POSITIVE LOGITS
    C
    1.04
    R
    0.90
    ل
    0.89
    K
    0.87
    L
    0.85
    P
    0.85
    M
    0.84
    E
    0.82
    T
    0.80
    N
    0.79
    Act Density 10.451%

    No Known Activations