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

    Neuronpedia

    INDEX
    Explanations

    .NET keywords and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Console
    0.46
    挔
    0.42
     Console
    0.42
    Models
    0.40
    Namespace
    0.39
     корпуса
    0.38
    InteropServices
    0.38
    Zug
    0.37
    Interop
    0.37
    Dong
    0.37
    POSITIVE LOGITS
    auto
    0.44
     auto
    0.43
     autof
    0.40
     cloudinary
    0.38
     sund
    0.38
    amanho
    0.38
     generic
    0.37
    ภู
    0.37
     autom
    0.37
     bad
    0.36
    Act Density 0.002%

    No Known Activations