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

    Neuronpedia

    INDEX
    Explanations

    files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dict
    -0.07
    皇
    -0.06
    akt
    -0.06
    plets
    -0.06
    นท
    -0.06
     games
    -0.06
    OTION
    -0.06
    ension
    -0.06
    Client
    -0.06
     linewidth
    -0.06
    POSITIVE LOGITS
     پژ
    0.07
     fundamentally
    0.07
    ्ग
    0.06
     знов
    0.06
     Seed
    0.06
    IFICATE
    0.06
    经营
    0.06
     overturn
    0.06
     Church
    0.06
     RouteServiceProvider
    0.06
    Act Density 0.049%

    No Known Activations