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

    Neuronpedia

    INDEX
    Explanations

    listing positive accommodation features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    主流
    0.81
     Shoe
    0.69
    Morgan
    0.69
     Commonly
    0.66
     Carousel
    0.65
     Analysis
    0.65
    Exponent
    0.64
    Multip
    0.64
    Diamonds
    0.64
    Ticker
    0.63
    POSITIVE LOGITS
     cocinar
    1.54
    民宿
    1.52
     cocina
    1.50
     cucina
    1.49
     comida
    1.48
     farmhouse
    1.37
     cooking
    1.34
     fiets
    1.33
     Airbnb
    1.33
     breakfasts
    1.31
    Act Density 0.056%

    No Known Activations