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

    Neuronpedia

    INDEX
    Explanations

    piecewise functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     कप
    -0.06
     artery
    -0.06
    eurs
    -0.06
     amac
    -0.06
     amp
    -0.06
     rog
    -0.06
     canned
    -0.06
     cooled
    -0.06
     Dmitry
    -0.06
     Sat
    -0.06
    POSITIVE LOGITS
     fitte
    0.07
    _hook
    0.07
     prevailed
    0.07
     Principles
    0.06
    wine
    0.06
     functionality
    0.06
     viene
    0.06
     pause
    0.06
    (wait
    0.06
    //****************************************************************************
    0.06
    Act Density 0.003%

    No Known Activations