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

    Neuronpedia

    INDEX
    Explanations

    sometimes, cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tous
    0.41
     சூ
    0.40
     nước
    0.39
     phospholipids
    0.39
     anew
    0.39
     none
    0.38
     each
    0.37
     excepto
    0.37
     unless
    0.36
     bằng
    0.36
    POSITIVE LOGITS
    这种情况
    0.79
     সেক্ষেত্রে
    0.79
     경우
    0.77
    Sometimes
    0.74
     sometimes
    0.73
     Sometimes
    0.73
     wtedy
    0.71
     경우에는
    0.70
     тоді
    0.70
     тогда
    0.69
    Act Density 0.084%

    No Known Activations