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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     संवेदनशील
    0.49
    ओके
    0.48
    िप्ट
    0.47
     opérations
    0.47
     цены
    0.47
    朋友
    0.47
     परवानगी
    0.46
     cancé
    0.46
     pedibus
    0.45
     amici
    0.45
    POSITIVE LOGITS
    0.41
     *
    0.40
     يم
    0.38
     Center
    0.36
     ¹
    0.36
     onwards
    0.36
     _
    0.35
     splurge
    0.35
     Montoya
    0.34
     f
    0.34
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.