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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Такой
    1.05
    Veja
    0.96
     Такие
    0.95
    aunque
    0.91
    ńskiej
    0.89
     dólares
    0.88
     станет
    0.88
    anakk
    0.88
     sonhos
    0.88
    IANS
    0.88
    POSITIVE LOGITS
    :
    0.84
    ,
    0.78
     destruction
    0.70
     classification
    0.69
     insufficient
    0.67
     sins
    0.67
     restriction
    0.66
     incorrectly
    0.66
    ，
    0.66
     reflectors
    0.65
    Act Density 0.003%

    No Known Activations