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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     підтрим
    0.54
    بت
    0.52
    tzmann
    0.52
     مردم
    0.52
     بڑھ
    0.50
    ٦
    0.50
    autres
    0.49
    tze
    0.48
     flound
    0.48
     поддер
    0.48
    POSITIVE LOGITS
    可以
    0.50
     );
    0.46
    /
    0.45
    Passive
    0.44
     κατο
    0.44
    Page
    0.44
     Lamont
    0.43
    <unused63>
    0.42
    臾
    0.42
     Stevens
    0.42
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.