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

    Neuronpedia

    INDEX
    Explanations

    ko, Kon, Kor, Kom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Co
    0.47
    ため
    0.43
    Co
    0.42
    实现的
    0.42
     ك
    0.41
    co
    0.41
     coincidence
    0.40
     mainly
    0.39
    UTION
    0.39
    e
    0.39
    POSITIVE LOGITS
    kor
    0.47
    kom
    0.46
     kor
    0.46
    Kon
    0.44
     Kor
    0.41
     Kon
    0.40
     Kom
    0.40
    Kom
    0.39
    opod
    0.38
    kon
    0.38
    Act Density 0.005%

    No Known Activations