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

    Neuronpedia

    INDEX
    Explanations

    ama

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    encing
    -0.07
    (success
    -0.07
    -Or
    -0.07
     rims
    -0.07
     newcomers
    -0.07
     meni
    -0.07
     bandwidth
    -0.07
     изменить
    -0.07
     (*.
    -0.07
     Menu
    -0.07
    POSITIVE LOGITS
     সালের
    0.08
     стаў
    0.08
    ọrọ
    0.08
     cuchar
    0.08
     ویلي
    0.08
    ոցի
    0.08
    'ebetso
    0.08
    স্পতিবার
    0.08
    ించిన
    0.08
    ugbọn
    0.07
    Act Density 0.002%

    No Known Activations