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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     analyzed
    1.01
    ახებ
    1.00
    <unused283>
    0.95
     defenses
    0.94
     inv
    0.92
     separated
    0.91
     travelers
    0.91
     juries
    0.90
    <unused1824>
    0.90
     sterilized
    0.89
    POSITIVE LOGITS
     Rubber
    0.99
     есть
    0.94
     ко
    0.87
     О
    0.86
     немного
    0.85
     режим
    0.83
    По
    0.83
     поток
    0.82
    是一款
    0.81
     Κ
    0.81
    Act Density 0.000%

    No Known Activations