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

    Neuronpedia

    INDEX
    Explanations

    code assignments/calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SHORT
    -0.07
     Notification
    -0.07
     Yah
    -0.06
     Huntington
    -0.06
     الض
    -0.06
     WebDriver
    -0.06
    ног
    -0.06
    oved
    -0.06
    ريف
    -0.06
    Suite
    -0.06
    POSITIVE LOGITS
     yapan
    0.07
     желез
    0.07
     feder
    0.06
    ajar
    0.06
    .NO
    0.06
     обращ
    0.06
     fibr
    0.06
     vaccinated
    0.06
    ApplicationContext
    0.06
     meanwhile
    0.06
    Act Density 0.055%

    No Known Activations