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

    Neuronpedia

    INDEX
    Explanations

    importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freely
    -0.06
    固定
    -0.06
     Pikachu
    -0.06
    陶
    -0.06
     başlan
    -0.06
     childish
    -0.06
    $config
    -0.06
    '/
    -0.06
    лада
    -0.06
     ngắn
    -0.06
    POSITIVE LOGITS
    ematics
    0.07
     المدينة
    0.07
     doubling
    0.07
    ates
    0.06
     Lorem
    0.06
     apple
    0.06
    Loc
    0.06
     축
    0.06
    оби
    0.06
    ejména
    0.06
    Act Density 0.042%

    No Known Activations