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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hazardous
    0.62
     corrosion
    0.61
     Submit
    0.60
    广大
    0.60
     dovrà
    0.60
     Corrosion
    0.59
     legado
    0.59
     Muitos
    0.59
     Entretanto
    0.59
     ඔ
    0.58
    POSITIVE LOGITS
     mindfulness
    0.96
     procrastination
    0.90
    習慣
    0.89
     meditation
    0.86
     housework
    0.86
     напомина
    0.83
     привы
    0.82
    注意力
    0.82
     Mindfulness
    0.81
     daydream
    0.79
    Act Density 0.765%

    No Known Activations