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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    a
    1.01
    𝐚
    0.79
    用来
    0.78
     Ausnahme
    0.77
    А
    0.76
    ्यां
    0.75
    а
    0.74
     aja
    0.73
    Пла
    0.72
    ア
    0.72
    POSITIVE LOGITS
     শিক
    0.94
     xăng
    0.93
     tricycle
    0.85
     coinbase
    0.84
    <unused577>
    0.83
     გახ
    0.83
    চ্ছন্ন
    0.82
    𝑝
    0.82
     _$_
    0.81
    नरी
    0.81
    Act Density 0.000%

    No Known Activations