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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ć
    1.01
     netto
    1.00
     apporter
    0.91
    う
    0.90
    ir
    0.83
     Aspir
    0.83
    iz
    0.81
     dựng
    0.77
     усилия
    0.77
    </b>
    0.77
    POSITIVE LOGITS
    اون
    1.02
     climbers
    1.02
     drunken
    0.97
     lentils
    0.95
    aan
    0.95
     pajamas
    0.95
     histological
    0.94
     😏
    0.94
     hysterical
    0.93
    tans
    0.93
    Act Density 0.000%

    No Known Activations