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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    م
    0.62
    ਼
    0.57
     theories
    0.56
    M
    0.56
    bodied
    0.55
    ­
    0.55
    pressed
    0.54
    coordinate
    0.54
    veil
    0.54
    atural
    0.54
    POSITIVE LOGITS
     Kudos
    0.88
    琅
    0.85
     первые
    0.82
     primero
    0.81
     erste
    0.79
     Excelente
    0.79
     clerk
    0.79
     pierws
    0.78
    োহণ
    0.78
    ിയത്
    0.78
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.