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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pra
    0.64
     uma
    0.60
     di
    0.60
     pekerjaan
    0.58
     bir
    0.57
     langsung
    0.57
     est
    0.57
     itu
    0.56
     separ
    0.55
     ein
    0.55
    POSITIVE LOGITS
    ‌്
    0.80
    ๎
    0.73
    ipede
    0.69
    ividades
    0.69
    ých
    0.67
     difíc
    0.67
    ەل
    0.67
    chetto
    0.66
    boxes
    0.65
    น์
    0.65
    Act Density 0.000%

    No Known Activations