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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caliber
    -0.07
    .herokuapp
    -0.07
     commissioned
    -0.06
     EXPER
    -0.06
    ensaje
    -0.06
     Animal
    -0.06
    principal
    -0.06
     Dover
    -0.06
     cessation
    -0.06
     нуж
    -0.06
    POSITIVE LOGITS
    Installed
    0.08
     엘
    0.07
     студ
    0.07
    ATES
    0.06
    .GetFiles
    0.06
    _pes
    0.06
    庭
    0.06
     ),
↵
    0.06
    ستر
    0.06
    _SCOPE
    0.06
    Act Density 0.271%

    No Known Activations