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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     denom
    1.56
     DJs
    1.52
     Unite
    1.48
    ফেসর
    1.47
     CONTRIBUTORS
    1.44
     Countries
    1.43
     accusations
    1.42
     Turks
    1.42
     Ombudsman
    1.41
     Staffordshire
    1.40
    POSITIVE LOGITS
    bread
    1.02
    y
    1.02
    스러
    0.97
    스러운
    0.94
    م
    0.88
    root
    0.88
     visok
    0.86
    B
    0.85
     خیر
    0.84
    ById
    0.83
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.