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

    Neuronpedia

    INDEX
    Explanations

    athletic events and races

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $)$
    1.00
     $=$
    0.92
    D
    0.88
     $\
    0.88
     "
    0.82
     (
    0.78
     De
    0.77
    ו
    0.76
    \_
    0.76
     =
    0.75
    POSITIVE LOGITS
     griega
    1.03
     rozpoc
    1.02
     sétimo
    0.99
     roda
    0.97
     petugas
    0.97
     jogador
    0.96
     duelo
    0.96
    тьяна
    0.95
     ballerina
    0.95
     minha
    0.94
    Act Density 0.012%

    No Known Activations