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

    Neuronpedia

    INDEX
    Explanations

    words starting with kun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ابل
    0.38
    لوار
    0.38
    CCNC
    0.36
    왓
    0.36
    cass
    0.36
    到了
    0.35
    PLY
    0.34
    着的
    0.34
    abba
    0.34
     Bhavan
    0.34
    POSITIVE LOGITS
     ку
    0.55
     कु
    0.47
     কু
    0.46
     쿠
    0.46
    कु
    0.45
     ಕು
    0.43
     Ку
    0.40
    ku
    0.40
    쿠
    0.39
    iku
    0.38
    Act Density 0.005%

    No Known Activations