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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     a
    0.54
    0.45
     বসিয়া
    0.44
              
    0.43
     abrog
    0.43
     raind
    0.41
     amending
    0.41
          
    0.41
    osof
    0.41
     universitaire
    0.41
    POSITIVE LOGITS
    i
    0.57
    வதற்கான
    0.55
    ed
    0.54
    חים
    0.54
    ਸ
    0.54
    ként
    0.53
    ה
    0.52
    কিছু
    0.52
    ي
    0.52
    ти
    0.51
    Act Density 0.000%

    No Known Activations