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

    Neuronpedia

    INDEX
    Explanations

    words starting with Ke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ুষ
    0.45
    графі
    0.41
    क
    0.39
    সাম্প্র
    0.38
    हुन्छ
    0.36
     اوف
    0.36
     पॉ
    0.36
    ък
    0.35
     काव्य
    0.35
    供應
    0.35
    POSITIVE LOGITS
     Ke
    0.70
    ystone
    0.68
    Ke
    0.66
     ke
    0.60
     KE
    0.58
    వలం
    0.57
    pler
    0.54
     Kepler
    0.53
    जरीवाल
    0.51
     Kee
    0.49
    Act Density 0.007%

    No Known Activations