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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     театр
    -0.08
    <textarea
    -0.07
     Pawn
    -0.07
    가
    -0.07
    <body
    -0.07
     Pregnancy
    -0.07
    横
    -0.07
     forg
    -0.06
     Rain
    -0.06
     بالأ
    -0.06
    POSITIVE LOGITS
    酯
    0.09
    xcd
    0.07
    稳固
    0.07
     clases
    0.07
    .Kind
    0.07
    仍未
    0.07
     capabilities
    0.07
     SPL
    0.07
     nost
    0.07
    Eliminar
    0.07
    Act Density 0.036%

    No Known Activations