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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Saf
    0.68
     பார்த்த
    0.65
     Hyper
    0.64
     hyper
    0.64
     Elon
    0.62
     Future
    0.62
     Futures
    0.61
     Safe
    0.61
     NDVI
    0.61
     beak
    0.60
    POSITIVE LOGITS
     groups
    1.10
     groupes
    1.09
     gruppi
    1.03
     Groups
    1.02
     entity
    1.00
     grupos
    1.00
     entities
    0.99
    Group
    0.99
     групп
    0.98
     zones
    0.97
    Act Density 0.313%

    No Known Activations