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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ↵↵
    1.16
     ו
    1.09
    ೃಹ
    1.04
     オレンジ
    1.04
     U
    1.02
    '،
    0.98
    ㅠ
    0.97
     S
    0.97
     มา
    0.96
     L
    0.96
    POSITIVE LOGITS
    .
    1.00
    มัน
    0.99
    関連記事
    0.97
    ̀i
    0.93
    ਾਂ
    0.91
    ্যন্তরীণ
    0.89
    acidade
    0.89
    ды
    0.87
    Wenn
    0.87
     maximize
    0.86
    Act Density 0.010%

    No Known Activations