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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ों
    0.82
     az
    0.80
    s
    0.72
     IN
    0.70
    N
    0.70
    给他
    0.67
     und
    0.66
     tire
    0.66
    च
    0.66
     tube
    0.65
    POSITIVE LOGITS
     działalności
    0.94
    мены
    0.91
    нской
    0.91
     አንዳንድ
    0.89
    товой
    0.88
     Эд
    0.86
     Тогда
    0.85
    льных
    0.84
    ܥ
    0.84
    ະພັນ
    0.83
    Act Density 0.000%

    No Known Activations