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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    F
    1.18
    C
    1.15
    N
    1.05
    J
    1.00
    U
    0.96
    Т
    0.95
    G
    0.94
    K
    0.94
    Z
    0.91
    B
    0.89
    POSITIVE LOGITS
    та
    0.95
    {
    0.90
    ти
    0.83
    ਾ
    0.80
    is
    0.74
    uctive
    0.74
    ள்ளது
    0.73
     limitations
    0.73
    acular
    0.70
    {//
    0.69
    Act Density 0.004%

    No Known Activations