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

    Neuronpedia

    INDEX
    Explanations

    clothing items and colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ඌ
    0.59
    لع
    0.57
     Ги
    0.57
    enl
    0.56
     Международ
    0.56
    Bộ
    0.56
     Omphalodes
    0.56
     Nós
    0.55
     Concrete
    0.55
    trajectory
    0.55
    POSITIVE LOGITS
     ajuda
    0.69
     livros
    0.69
     tengo
    0.68
     dejar
    0.68
     tuvieron
    0.67
     mémoire
    0.66
     musia
    0.66
     fucking
    0.65
     menulis
    0.65
     satın
    0.64
    Act Density 0.001%

    No Known Activations