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

    Neuronpedia

    INDEX
    Explanations

    web and code files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ônica
    -0.79
    ený
    -0.76
     precio
    -0.72
    ственную
    -0.72
     طریق
    -0.72
     часть
    -0.71
     commitment
    -0.71
     umowy
    -0.71
    Saying
    -0.69
     Pal
    -0.69
    POSITIVE LOGITS
     Web
    1.34
     web
    1.14
     print
    1.09
    print
    1.03
    Web
    0.96
     waschen
    0.90
     vốn
    0.90
     qtd
    0.87
    qtd
    0.87
    web
    0.86
    Act Density 0.004%

    No Known Activations