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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    機能
    -0.07
    >a
    -0.06
    elson
    -0.06
    world
    -0.06
    plates
    -0.06
     NC
    -0.06
    mys
    -0.06
    hu
    -0.06
     bear
    -0.06
     Pointer
    -0.06
    POSITIVE LOGITS
     kardeş
    0.07
     {[%
    0.07
    meer
    0.07
    \Session
    0.06
    ographer
    0.06
    agem
    0.06
     Yugoslavia
    0.06
     Midnight
    0.06
    設計
    0.06
    Deferred
    0.06
    Act Density 0.019%

    No Known Activations