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

    Neuronpedia

    INDEX
    Explanations

    working

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     working
    -0.71
    Working
    -0.66
    Worked
    -0.66
     Worked
    -0.65
     worked
    -0.63
     work
    -0.62
     travaillé
    -0.61
    worked
    -0.58
     Working
    -0.57
    Work
    -0.57
    POSITIVE LOGITS
    transQ
    0.68
    :✨
    0.64
    ]--;
    0.59
    aarrggbb
    0.57
     Commanders
    0.57
    webElementXpaths
    0.57
    complexContent
    0.56
     ligiloj
    0.55
     Kinetics
    0.55
    afficheront
    0.55
    Act Density 0.074%

    No Known Activations