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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    !
    0.93
    行走
    0.89
    这里
    0.88
    FROM
    0.87
    }}_{\
    0.86
    出
    0.86
    날
    0.86
    ۣ
    0.84
    th
    0.83
    穫
    0.83
    POSITIVE LOGITS
     externalities
    1.14
     excitations
    1.12
    ம்பரிய
    1.02
     eléctricos
    1.01
     diante
    0.99
     affidavits
    0.98
     extraordin
    0.97
    imizin
    0.95
     ব্যবস্থ
    0.94
     redundancies
    0.93
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.