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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    奔赴
    -0.08
    <long
    -0.07
     footing
    -0.07
     chăm
    -0.07
    甯
    -0.07
    也只是
    -0.07
     clothing
    -0.07
    หว
    -0.07
     intention
    -0.07
    憧憬
    -0.07
    POSITIVE LOGITS
    ()));
    0.08
    خفض
    0.08
    fen
    0.08
    VER
    0.07
    七十
    0.07
    aviest
    0.07
    ometimes
    0.07
    ')."
    0.07
    _regions
    0.07
    RO
    0.07
    Act Density 0.001%

    No Known Activations