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

    Neuronpedia

    INDEX
    Explanations

    language translation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    باح
    -0.08
     obtainable
    -0.08
    -0.08
     obtain
    -0.07
    зв
    -0.07
     ബന്ധപ്പെട്ട
    -0.07
    线
    -0.07
     bean
    -0.07
    -0.07
     ilgili
    -0.07
    POSITIVE LOGITS
    -Saint
    0.09
     достиг
    0.08
     purely
    0.08
     технологии
    0.08
    -carbon
    0.08
     detects
    0.08
     ակտիվ
    0.08
     פע
    0.08
     যদি
    0.08
    -icons
    0.07
    Act Density 0.002%
    No Known Activations