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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    timestamp
    2.35
    ভারত
    2.18
    ת
    2.16
    า
    1.92
    ين
    1.91
    an
    1.89
    不必
    1.89
    kungan
    1.88
    nobyl
    1.87
    스크
    1.83
    POSITIVE LOGITS
    (\
    1.65
    ("("
    1.64
     readonly
    1.63
    <unused30>
    1.62
     Microbial
    1.58
    emotion
    1.56
    Emotion
    1.55
    ۣ
    1.50
    ൬
    1.48
     inroads
    1.47
    Act Density 0.081%

    No Known Activations