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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ob
    0.50
    Ens
    0.50
    defaults
    0.47
     вари
    0.46
    Х
    0.44
    শোর
    0.43
    سط
    0.43
    alimentation
    0.43
    塑造
    0.43
    🗨
    0.43
    POSITIVE LOGITS
     Jesús
    0.64
     iria
    0.59
     Roberto
    0.59
     LeBron
    0.57
     Grammy
    0.56
     Meghan
    0.56
     correctAnswer
    0.55
     Oprah
    0.55
     dopo
    0.55
     Cristina
    0.55
    Act Density 0.000%

    No Known Activations