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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ங்கிணை
    1.07
    ِی
    1.02
    Ϭ
    1.00
    ሽን
    0.93
    追加
    0.93
    ্লীল
    0.92
    ignores
    0.91
    тык
    0.91
    ниці
    0.90
    変
    0.90
    POSITIVE LOGITS
    1.34
     Investigative
    1.05
    uck
    0.99
     IN
    0.95
     It
    0.94
    aan
    0.92
     Caravan
    0.91
    useppe
    0.90
    ias
    0.90
    1
    0.89
    Act Density 0.071%

    No Known Activations