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

    Neuronpedia

    INDEX
    Explanations

    code and variable names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invasive
    -0.07
    _playing
    -0.07
    زو
    -0.07
     quanh
    -0.07
     Kadın
    -0.06
     Dynamic
    -0.06
    ()%
    -0.06
     intrusive
    -0.06
     расч
    -0.06
    ่าย
    -0.06
    POSITIVE LOGITS
    ],[-
    0.06
     jur
    0.06
     tam
    0.06
    .ConnectionStrings
    0.06
    _
↵
↵
    0.06
    patibility
    0.06
     kur
    0.06
    _APB
    0.06
    ,state
    0.05
     rav
    0.05
    Act Density 0.400%

    No Known Activations