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

    Neuronpedia

    INDEX
    Explanations

    Business, policies, and school lessons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Asi
    -0.09
     Mohamed
    -0.09
     Carolina
    -0.08
     Dorset
    -0.08
     Lanka
    -0.08
     Adult
    -0.08
    ומי
    -0.08
     fore
    -0.08
     kicking
    -0.08
     mango
    -0.08
    POSITIVE LOGITS
     analiza
    0.08
    Wise
    0.08
    sic
    0.07
    0.07
    .jpeg
    0.07
    Sunny
    0.07
    oy
    0.07
    പ്പെടുത്ത
    0.07
     assert
    0.07
     menyediakan
    0.07
    Act Density 0.253%
    No Known Activations