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

    Neuronpedia

    INDEX
    Explanations

    K-Means clustering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     most
    0.70
     first
    0.70
     initial
    0.69
     enumerable
    0.66
     youthful
    0.66
     hairstyle
    0.65
     hairc
    0.65
     Peralta
    0.65
     wardrobe
    0.64
     filepath
    0.64
    POSITIVE LOGITS
    BrowserRouter
    0.60
    GEBURTS
    0.57
    Neces
    0.57
    Alles
    0.57
    Ар
    0.56
    TRANSPORT
    0.56
    Рас
    0.55
    󰀄
    0.55
    Puzzle
    0.55
    Список
    0.55
    Act Density 0.464%

    No Known Activations