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

    Neuronpedia

    INDEX
    Explanations

    information and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пу
    0.50
    ুল
    0.49
    стви
    0.47
    гу
    0.46
     संघटना
    0.46
    рите
    0.45
     kampus
    0.45
    сите
    0.44
    ຫຼື
    0.44
    鑒
    0.43
    POSITIVE LOGITS
     Hòa
    0.46
    玤
    0.46
     ৫০০
    0.45
    Isaiah
    0.45
     opdracht
    0.43
     creates
    0.43
     submission
    0.42
     Gets
    0.41
     subtracting
    0.41
    寻找
    0.41
    Act Density 0.002%

    No Known Activations