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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    니
    0.41
     vets
    0.41
     nails
    0.38
     warts
    0.38
    пер
    0.38
    িনি
    0.37
     idx
    0.37
     guts
    0.37
     ১ম
    0.37
    IR
    0.37
    POSITIVE LOGITS
     Saviour
    0.42
     ocorrer
    0.38
     Jimin
    0.38
     Fernand
    0.38
     אטאטורק
    0.37
     XXIII
    0.36
     Zeeman
    0.36
    人民政府
    0.36
    不會
    0.36
     UILabel
    0.35
    Act Density 0.003%

    No Known Activations