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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     went
    0.50
     हमारी
    0.47
     ہماری
    0.46
     Elovl
    0.46
    یم
    0.45
    چھے
    0.45
     obscur
    0.45
    went
    0.44
     persever
    0.44
     peligro
    0.44
    POSITIVE LOGITS
     WHETHER
    0.45
    ទី
    0.44
    [,,"
    0.44
    অর্থাৎ
    0.44
    㧍
    0.43
     DISNEY
    0.40
    ហារ
    0.40
    汢
    0.39
    ᱷ
    0.38
    ไม่ได้
    0.38
    Act Density 0.008%

    No Known Activations