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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Avenue
    -0.07
    sorted
    -0.07
     latest
    -0.07
    Tuesday
    -0.07
     crew
    -0.07
    -general
    -0.07
     satış
    -0.06
     Faculty
    -0.06
     Charles
    -0.06
     bare
    -0.06
    POSITIVE LOGITS
     pornofilm
    0.07
    =UTF
    0.06
    searchModel
    0.06
    .Scheme
    0.06
    Кон
    0.06
    .FromResult
    0.06
     multer
    0.06
    �行
    0.06
    ')->__('
    0.06
    луг
    0.06
    Act Density 0.007%

    No Known Activations