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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Constraints
    0.74
     Innovative
    0.73
    льта
    0.72
     Weapons
    0.68
     underwater
    0.67
     Diagnostics
    0.67
     berth
    0.67
     hypotheses
    0.66
     Bibliography
    0.65
     spatially
    0.65
    POSITIVE LOGITS
    Сі
    0.89
    Пі
    0.86
    К
    0.86
     iniziale
    0.84
    Созда
    0.84
    Οι
    0.80
    Nuestro
    0.80
    ched
    0.79
    ఈ
    0.79
    सामाजिक
    0.78
    Act Density 0.009%

    No Known Activations