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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    jenigen
    2.02
     testament
    1.88
    ための
    1.62
    ively
    1.61
    за
    1.59
     Vergangenheit
    1.54
    सायनिक
    1.47
     Merkel
    1.47
    ą
    1.46
    ◄
    1.45
    POSITIVE LOGITS
    ერის
    2.31
    न
    2.13
    on
    2.08
    𝚝
    1.98
    ḏ
    1.94
    ták
    1.93
    ের
    1.91
    ཱ
    1.88
    𝚙
    1.87
     לפני
    1.87
    Act Density 0.000%

    No Known Activations