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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     abras
    1.20
    েলের
    1.15
    sächlich
    1.07
    АН
    1.05
    也沒有
    1.04
     moneda
    1.04
    gehen
    1.03
     precluded
    1.03
    ANCIAL
    1.01
     PLHIV
    1.00
    POSITIVE LOGITS
     k
    0.96
     then
    0.90
    R
    0.89
    ,
    0.87
    value
    0.87
    ch
    0.85
     value
    0.84
     shown
    0.84
    en
    0.83
    k
    0.83
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.