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

    Neuronpedia

    INDEX
    Explanations

    Spanish language, universities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    地段
    -0.07
    urahan
    -0.07
     traverse
    -0.07
    enddate
    -0.07
    deadline
    -0.07
    entrée
    -0.07
    password
    -0.07
    永远
    -0.07
    ersistent
    -0.06
     cert
    -0.06
    POSITIVE LOGITS
                             ↵
    0.08
    _In
    0.07
    Uploaded
    0.07
    )').
    0.07
    >Total
    0.07
    Animal
    0.07
    _IM
    0.07
    >-->↵
    0.07
     FOX
    0.07
     spice
    0.07
    Act Density 1.987%

    No Known Activations