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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝚊
    0.76
     знали
    0.61
    𝚝
    0.60
     valorar
    0.60
    ेश्वरी
    0.59
    iu
    0.57
    ेशन
    0.57
    িতে
    0.56
    tól
    0.56
     condem
    0.55
    POSITIVE LOGITS
    াভাবিক
    0.60
    ح
    0.58
    пи
    0.57
    дру
    0.54
     اتارنا
    0.53
    🔥🔥
    0.53
    ிற்ப
    0.53
     infix
    0.51
     rey
    0.51
     afterthought
    0.50
    Act Density 0.032%

    No Known Activations