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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     its
    -1.07
     to
    -1.05
     on
    -1.04
     a
    -1.04
    män
    -1.00
     pág
    -0.98
     all
    -0.97
    бая
    -0.97
    batik
    -0.96
     mendengar
    -0.95
    POSITIVE LOGITS
     EIGHT
    1.06
     frequentemente
    1.05
    越多
    1.03
    ޭ
    1.01
     frecuentemente
    1.01
     recentemente
    0.99
    aliśmy
    0.99
     そば
    0.99
     plumme
    0.98
     adept
    0.98
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.