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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     trash
    1.12
     புரா
    1.07
    wegian
    1.03
    Zeneca
    1.03
     DDoS
    0.96
    ंगिक
    0.95
     erneut
    0.94
    Photon
    0.94
    Prema
    0.94
     cos
    0.93
    POSITIVE LOGITS
     Importance
    1.00
     inspirations
    0.98
    هِ
    0.97
     educated
    0.97
     handcuffed
    0.93
    riages
    0.92
    دا
    0.91
    شاء
    0.91
     distinctions
    0.91
     Where
    0.91
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.