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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ח
    0.51
    грамм
    0.50
     menyatakan
    0.50
     lingkaran
    0.48
    Б
    0.48
     cerita
    0.47
    B
    0.47
     Ketua
    0.47
    ब
    0.47
     adalah
    0.46
    POSITIVE LOGITS
    ো
    0.57
     ብዙውን
    0.55
    ി
    0.50
    ið
    0.49
    িগ্ন
    0.47
    ಿಗಳು
    0.47
    utlich
    0.46
     datafile
    0.45
     patched
    0.45
    getImageFolder
    0.44
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.