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

    Neuronpedia

    INDEX
    Explanations

    bubble sort, merge sort, arbitrage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     struggle
    1.00
    használ
    0.99
     basada
    0.97
     கட்டமை
    0.97
    _,
    0.97
     laissez
    0.96
     fara
    0.96
     waarmee
    0.95
    ্লাহ
    0.94
     puso
    0.91
    POSITIVE LOGITS
    સ
    1.22
    н
    1.17
    本质
    1.17
    ০
    1.14
    ोत्सव
    1.12
    ง
    1.09
    ্ত
    1.09
    hole
    1.08
    소스
    1.07
    bling
    1.07
    Act Density 0.140%

    No Known Activations