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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    у
    1.14
    letzt
    0.99
    િલે
    0.98
    қ
    0.97
    Khan
    0.94
    тра
    0.92
     এজন্য
    0.90
    听
    0.89
    Ding
    0.89
    В
    0.87
    POSITIVE LOGITS
     interes
    1.57
    aadhar
    1.53
    civ
    1.42
    cakes
    1.38
     Shortcuts
    1.37
    rets
    1.36
     pacif
    1.36
    lis
    1.35
    Primitives
    1.34
    pesar
    1.33
    Act Density 0.000%

    No Known Activations