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

    Neuronpedia

    INDEX
    Explanations

    inject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AlertDialog
    -0.09
     stupidity
    -0.07
     AlertDialog
    -0.07
     mView
    -0.06
     isChecked
    -0.06
    ürlich
    -0.06
     "
    -0.06
     žen
    -0.06
     Serial
    -0.06
    Rad
    -0.06
    POSITIVE LOGITS
     nhánh
    0.06
    <Article
    0.06
     Layer
    0.06
     Contrast
    0.06
    aspers
    0.06
     dispenser
    0.06
     Noon
    0.06
     fint
    0.06
     کامل
    0.06
     Ensemble
    0.06
    Act Density 0.002%

    No Known Activations