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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لاح
    -0.08
     mensal
    -0.08
    商城
    -0.07
     franqu
    -0.07
     humm
    -0.07
    _messages
    -0.07
     ব্য
    -0.07
    Merchant
    -0.07
    chi
    -0.07
    务
    -0.07
    POSITIVE LOGITS
     संभावना
    0.09
    텔
    0.08
     aimé
    0.08
     Ile
    0.08
     Perspective
    0.07
     ट्रेन
    0.07
    Wanted
    0.07
     Predictor
    0.07
    ైనా
    0.07
     Negoti
    0.07
    Act Density 0.042%

    No Known Activations