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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     рів
    0.86
    0.85
    ième
    0.84
    ה
    0.83
     ieri
    0.82
            
    0.80
        
    0.78
     risposta
    0.77
    0.76
     וי
    0.76
    POSITIVE LOGITS
     fulfills
    0.79
     fulfils
    0.79
     budding
    0.78
     composting
    0.78
     fulfilling
    0.77
     fabric
    0.75
     peaceful
    0.75
     subspecies
    0.75
    圿
    0.73
     profitable
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.