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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    a
    1.15
    ant
    1.04
    ม
    0.97
    ud
    0.94
    ian
    0.94
    read
    0.89
    ล
    0.87
    '};
    0.87
    ড়
    0.86
    load
    0.86
    POSITIVE LOGITS
     بری
    0.89
     меда
    0.89
     большин
    0.83
     לס
    0.83
     éstas
    0.82
     المستوى
    0.81
     prerogative
    0.81
    ☏
    0.80
     περισσότε
    0.78
     рома
    0.77
    Act Density 0.009%

    No Known Activations