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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     operaciones
    1.28
     Oficina
    1.26
    وى
    1.25
     Convent
    1.17
     Trabaj
    1.15
    嗯
    1.15
     Brid
    1.15
    今年
    1.14
     Nuggets
    1.12
     Олимпий
    1.11
    POSITIVE LOGITS
    ρη
    0.94
    ृत्य
    0.93
    ),],
    0.92
     येतात
    0.89
    ंद्व
    0.88
    ట్ల
    0.87
     violating
    0.85
    რის
    0.85
    *)(
    0.85
    シス
    0.85
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.