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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    igu
    0.41
    fat
    0.40
    -"
    0.38
     fats
    0.38
     ep
    0.36
    ści
    0.36
     пара
    0.36
    Smooth
    0.35
     smooth
    0.35
    Fat
    0.35
    POSITIVE LOGITS
     utilises
    0.45
    }={\
    0.44
     PREFIX
    0.42
     なさい
    0.41
     प्राथमिक
    0.40
     पिंक
    0.39
    ARIFF
    0.38
    ার্থে
    0.38
     عامل
    0.38
    ებში
    0.37
    Act Density 0.002%

    No Known Activations