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

    Neuronpedia

    INDEX
    Explanations

    toc or contents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sanctions
    -0.08
     vu
    -0.07
    嗪
    -0.07
     prank
    -0.07
     vaccine
    -0.06
     Api
    -0.06
     server
    -0.06
     PIE
    -0.06
    ValueCollection
    -0.06
    ningen
    -0.06
    POSITIVE LOGITS
    .GetDirectoryName
    0.07
    .Reflection
    0.07
     Есть
    0.07
     spokes
    0.07
    משקל
    0.07
    <decimal
    0.07
     Москвы
    0.06
     путеш
    0.06
    %.↵↵
    0.06
    ดวง
    0.06
    Act Density 0.004%

    No Known Activations