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

    Neuronpedia

    INDEX
    Explanations

    director, manager roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vu
    -0.06
    벤
    -0.06
    zte
    -0.06
    ланд
    -0.06
     homosex
    -0.06
    ennifer
    -0.06
     visceral
    -0.06
    押
    -0.06
    	stats
    -0.05
     aracılığıyla
    -0.05
    POSITIVE LOGITS
     |
    0.07
     Lime
    0.06
     headphones
    0.06
     طر
    0.06
     PRE
    0.06
     Dart
    0.06
    획
    0.06
    Mexico
    0.06
     وحدة
    0.06
    IEW
    0.06
    Act Density 0.001%

    No Known Activations