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

    Neuronpedia

    INDEX
    Explanations

    both / breaking down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aryng
    0.41
    ソッド
    0.41
    raš
    0.41
     Hence
    0.39
    ૅ
    0.38
    ؟.
    0.37
     banjir
    0.37
     attempting
    0.37
     seguente
    0.37
     ბ
    0.37
    POSITIVE LOGITS
     zowel
    1.12
     both
    1.11
     sowohl
    1.05
    both
    1.04
     سواء
    1.01
     både
    0.96
     zarówno
    0.95
    ทั้ง
    0.92
     BOTH
    0.91
    Both
    0.88
    Act Density 0.347%

    No Known Activations