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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    㫻
    0.52
    緍
    0.51
    氧化
    0.50
    톄
    0.48
    聝
    0.48
    茠
    0.48
    脌
    0.47
    慓
    0.47
    ModelGrid
    0.46
     physiologically
    0.46
    POSITIVE LOGITS
    ?
    0.70
     But
    0.62
     tetapi
    0.61
    But
    0.61
     However
    0.60
    It
    0.59
     They
    0.58
    However
    0.56
     but
    0.56
     tersebut
    0.55
    Act Density 0.000%

    No Known Activations