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

    Neuronpedia

    INDEX
    Explanations

    system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hPa
    -0.07
     vite
    -0.07
     pointed
    -0.07
    setLabel
    -0.06
     봐
    -0.06
     matchups
    -0.06
    .Dimension
    -0.06
    <Test
    -0.06
     sch
    -0.06
    optimized
    -0.06
    POSITIVE LOGITS
     tele
    0.06
    /',
    0.06
     peel
    0.06
    incy
    0.06
    -admin
    0.06
     communicating
    0.06
     polls
    0.06
    .firebase
    0.06
    _ok
    0.05
     ；
    0.05
    Act Density 0.028%

    No Known Activations