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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pred
    -0.07
    _library
    -0.06
    BUILD
    -0.06
     μ
    -0.06
     MX
    -0.06
    _gallery
    -0.06
     الاس
    -0.06
    /dev
    -0.06
     الس
    -0.06
     DIV
    -0.06
    POSITIVE LOGITS
     розвитку
    0.07
    лин
    0.06
    utters
    0.06
     світі
    0.06
    tık
    0.06
    JOR
    0.06
    }"↵
    0.06
     acos
    0.06
     etmiştir
    0.06
    ınma
    0.06
    Act Density 2.413%

    No Known Activations