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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lu
    -0.07
     waste
    -0.07
     wast
    -0.07
    LU
    -0.07
     Flame
    -0.06
     pubs
    -0.06
    -create
    -0.06
     Portfolio
    -0.06
    prop
    -0.06
     werde
    -0.06
    POSITIVE LOGITS
    -api
    0.07
    (window
    0.07
    .Popen
    0.07
    rey
    0.06
    Introduction
    0.06
     　　　　　　　　　　　
    0.06
    ／／
    0.06
    SESSION
    0.06
    0.06
    /App
    0.06
    Act Density 0.030%

    No Known Activations