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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    atic
    0.50
     Relief
    0.49
     Fitness
    0.48
    ns
    0.47
    raising
    0.46
    inal
    0.46
    ūr
    0.46
    am
    0.46
    quer
    0.46
    doctoral
    0.45
    POSITIVE LOGITS
        
    0.46
    лей
    0.45
     beled
    0.43
    板
    0.43
     knives
    0.43
    кей
    0.42
     crud
    0.42
    части
    0.42
    被
    0.42
          
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.