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

    Neuronpedia

    INDEX
    Explanations

    Kh followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vitt
    0.47
    കൊ
    0.41
    бурге
    0.39
    чески
    0.37
     উঠেছিল
    0.36
    द्योगिकी
    0.36
    Anyone
    0.35
    が多く
    0.35
    жного
    0.35
    കു
    0.35
    POSITIVE LOGITS
     kh
    0.76
     Kh
    0.73
    Kh
    0.73
     ख
    0.55
    kh
    0.52
    Khal
    0.52
    khar
    0.50
     Khar
    0.50
     khal
    0.50
    KH
    0.48
    Act Density 0.004%

    No Known Activations