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

    Neuronpedia

    INDEX
    Explanations

    elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trevor
    -0.07
    stdexcept
    -0.07
    思考
    -0.07
    喜爱
    -0.07
     dive
    -0.07
     muse
    -0.07
    adio
    -0.07
    dimensions
    -0.07
    Math
    -0.07
     sug
    -0.07
    POSITIVE LOGITS
    或多或
    0.07
    二是
    0.07
     UserController
    0.07
    木耳
    0.07
    wap
    0.07
    arda
    0.07
    /do
    0.07
    Portland
    0.07
    ун
    0.07
     TER
    0.07
    Act Density 0.003%

    No Known Activations