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

    Neuronpedia

    INDEX
    Explanations

    Greek/Latin suffixes for "-ology", "-ocracy", "-philia", "-ic", "-ous"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    1.16
    on
    1.09
    ar
    1.05
    ap
    0.98
    al
    0.96
    س
    0.94
    os
    0.89
    s
    0.88
    en
    0.87
    ans
    0.87
    POSITIVE LOGITS
     când
    0.81
     tôi
    0.79
     парк
    0.75
     thì
    0.74
     đó
    0.72
     ili
    0.71
     chúng
    0.71
     là
    0.71
     peruse
    0.71
     gdy
    0.70
    Act Density 0.037%

    No Known Activations