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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lalu
    0.89
     Poo
    0.86
     Wohn
    0.84
     Parking
    0.83
     Lalu
    0.83
     Paula
    0.82
     Pens
    0.78
     Quakers
    0.78
     personas
    0.77
     Iceland
    0.77
    POSITIVE LOGITS
     प्रणाली
    0.67
    ε
    0.66
    maximal
    0.65
    遵循
    0.64
    dressing
    0.63
    それが
    0.63
    ⵚ
    0.63
    시스템
    0.62
    製
    0.62
    ilità
    0.61
    Act Density 0.000%

    No Known Activations