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

    Neuronpedia

    INDEX
    Explanations

    Restaurants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     addresses
    -0.07
     papers
    -0.07
     میدان
    -0.07
    Salary
    -0.06
    وجد
    -0.06
    احث
    -0.06
     studi
    -0.06
     paper
    -0.06
     yc
    -0.06
    -0.06
    POSITIVE LOGITS
     Ill
    0.08
    Blo
    0.07
    нюю
    0.06
     Milky
    0.06
    次
    0.06
    %↵↵
    0.06
     inté
    0.06
     Simone
    0.06
    ]+"
    0.06
    анная
    0.06
    Act Density 0.019%

    No Known Activations