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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     prerogative
    1.01
     जानते
    0.98
    ిన
    0.95
     harmonious
    0.93
     striking
    0.91
     trattamento
    0.91
     integral
    0.89
    bilt
    0.89
    اتے
    0.89
    ల
    0.86
    POSITIVE LOGITS
    texto
    1.12
     chaper
    1.08
    빚
    1.04
     jazdy
    1.02
    molecule
    1.00
    引用
    0.99
    luc
    0.98
     girder
    0.96
    ום
    0.95
     ваши
    0.94
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.