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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     الدني
    -0.07
    ᠢ
    -0.07
     QAction
    -0.07
     ingin
    -0.07
     Tử
    -0.06
     irreversible
    -0.06
    Lesson
    -0.06
    恋人
    -0.06
    utral
    -0.06
    ♂
    -0.06
    POSITIVE LOGITS
    大股东
    0.07
    ktör
    0.07
     Oscar
    0.07
    =w
    0.07
     UF
    0.07
     folds
    0.07
     SERVICES
    0.07
     Barbara
    0.07
     К
    0.07
     соответств
    0.07
    Act Density 0.004%

    No Known Activations