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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ysteem
    0.90
    ภัย
    0.89
    chten
    0.84
    ੀ
    0.82
    ेक्ट
    0.81
     পাবে
    0.81
     Enem
    0.81
    deka
    0.81
     conter
    0.81
    larından
    0.80
    POSITIVE LOGITS
     stares
    1.02
     вста
    1.01
     spit
    0.97
     figsize
    0.97
     furrow
    0.96
    tiff
    0.94
    美
    0.94
    やって
    0.93
     fais
    0.93
    ニュ
    0.93
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.