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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     उर्फ
    0.50
     የ
    0.48
    娶
    0.47
     البي
    0.45
    PHONE
    0.45
     ማለት
    0.45
     навіть
    0.45
    clazz
    0.45
     比
    0.44
     බ
    0.44
    POSITIVE LOGITS
     specialists
    0.52
    ᾖ
    0.52
    '
    0.50
     musician
    0.47
     peonies
    0.47
     author
    0.46
     I
    0.45
     introductory
    0.45
     letter
    0.45
    estes
    0.44
    Act Density 0.000%

    No Known Activations