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

    Neuronpedia

    INDEX
    Explanations

    you're are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     satu
    -0.07
    或
    -0.07
    lobs
    -0.07
     همچنین
    -0.06
    adığı
    -0.06
    وى
    -0.06
    جيل
    -0.06
     далі
    -0.06
    看到
    -0.06
    зу
    -0.06
    POSITIVE LOGITS
     getArguments
    0.07
    ffect
    0.06
     constitutional
    0.06
     Adoption
    0.06
     getItem
    0.06
    公开
    0.06
     rot
    0.06
     задов
    0.06
    itions
    0.06
     titleLabel
    0.06
    Act Density 0.015%

    No Known Activations