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

    Neuronpedia

    INDEX
    Explanations

    software configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apiro
    -0.07
    warning
    -0.06
    StdString
    -0.06
    .isdigit
    -0.06
     dismissing
    -0.06
    Fizz
    -0.06
    Word
    -0.06
    での
    -0.06
     Dirt
    -0.06
    ضة
    -0.06
    POSITIVE LOGITS
     EMAIL
    0.07
    .Alignment
    0.06
    ائب
    0.06
     Installer
    0.06
     eyebrows
    0.06
    .Inventory
    0.06
     mạng
    0.06
    ائي
    0.06
    _arrow
    0.06
    /views
    0.06
    Act Density 0.118%

    No Known Activations