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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Objects
    -0.08
    /articles
    -0.07
    /im
    -0.06
     sebuah
    -0.06
    &p
    -0.06
    /static
    -0.06
    [d
    -0.06
     biography
    -0.06
     Epid
    -0.06
    Association
    -0.06
    POSITIVE LOGITS
     mats
    0.06
     minHeight
    0.06
    }</
    0.06
    (Expected
    0.06
     Heather
    0.06
    eci
    0.06
     CONTENT
    0.06
    .Nil
    0.06
     exited
    0.06
     curls
    0.06
    Act Density 0.012%

    No Known Activations