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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     被
    -0.07
     ucfirst
    -0.07
    цю
    -0.07
    -century
    -0.07
     Hew
    -0.06
     Fried
    -0.06
    lld
    -0.06
    iễ
    -0.06
     diets
    -0.06
    џџ
    -0.06
    POSITIVE LOGITS
     one
    0.07
    」↵
    0.06
     formulated
    0.06
     Regulation
    0.06
    Foundation
    0.06
    /validation
    0.06
     followers
    0.06
     uncovered
    0.06
    .Cons
    0.06
    Ensure
    0.06
    Act Density 0.009%

    No Known Activations