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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     attrs
    1.04
     Refugees
    1.01
     Craft
    0.96
     biologiques
    0.93
     Routes
    0.90
     Alber
    0.90
     ARTS
    0.90
     Workshops
    0.90
     Roles
    0.90
     prides
    0.89
    POSITIVE LOGITS
    ма
    0.98
    มาชิก
    0.95
    ḿ
    0.91
    casting
    0.90
    обходи
    0.89
    는
    0.89
    نامہ
    0.88
    Ę
    0.88
    뢨
    0.87
    ा
    0.87
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.