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

    Neuronpedia

    INDEX
    Explanations

    know it or iteration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⴹ
    0.48
    டையே
    0.41
    觕
    0.38
    喹
    0.38
    0.38
     علامت
    0.38
    ញ្ញ
    0.38
    цна
    0.38
     cysteine
    0.37
    䧺
    0.37
    POSITIVE LOGITS
    IT
    2.23
     IT
    2.22
     Iter
    2.13
    Iter
    2.09
     Iterator
    2.05
    <0x8A>
    2.03
     iterator
    2.02
     iter
    1.98
    迭代
    1.91
    Iterator
    1.89
    Act Density 0.207%

    No Known Activations