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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    a
    1.00
    at
    0.99
    al
    0.98
    er
    0.94
    economic
    0.89
    in
    0.87
    on
    0.86
    are
    0.86
    n
    0.84
    like
    0.82
    POSITIVE LOGITS
    肝
    0.82
    栨
    0.80
    टरी
    0.73
     фор
    0.70
    锂
    0.70
    眹
    0.69
     DISPLAYSURF
    0.69
    什么
    0.68
    )：
    0.68
     उन्‍ह
    0.67
    Act Density 0.002%

    No Known Activations