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

    Neuronpedia

    INDEX
    Explanations

    signature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nutrient
    -0.08
    éraux
    -0.08
     Kuala
    -0.07
     خور
    -0.07
     supper
    -0.07
     speculative
    -0.07
     غذ
    -0.07
     caisse
    -0.07
     Examiner
    -0.07
    quin
    -0.07
    POSITIVE LOGITS
     स्मार्ट
    0.09
     Workflow
    0.08
     Smart
    0.08
    smart
    0.08
    SAFE
    0.08
    智能
    0.08
     seamlessly
    0.08
     пользов
    0.08
    Workflow
    0.08
     Upload
    0.08
    Act Density 0.005%

    No Known Activations