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

    Neuronpedia

    INDEX
    Explanations

    legal/policy documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     implied
    -0.08
          ↵      ↵
    -0.07
     Meyer
    -0.06
     Hog
    -0.06
    我們
    -0.06
    DataProvider
    -0.06
    _middle
    -0.06
     alex
    -0.06
    이
    -0.06
     Commun
    -0.06
    POSITIVE LOGITS
    (pair
    0.07
    (Collections
    0.06
     العربية
    0.06
    (Clone
    0.06
     Maui
    0.06
    EU
    0.06
    .Formatting
    0.06
    (IntPtr
    0.06
    -generator
    0.06
     disillusion
    0.06
    Act Density 0.021%

    No Known Activations