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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .DEBUG
    -0.06
    mart
    -0.06
    Lake
    -0.06
    ilos
    -0.06
    Pets
    -0.06
    ского
    -0.06
    Mart
    -0.06
    ضة
    -0.06
    //**↵
    -0.06
     Jen
    -0.06
    POSITIVE LOGITS
     physically
    0.07
     assortment
    0.07
    (coll
    0.07
     Numerous
    0.07
     :)
    0.06
    éc
    0.06
    ).↵↵↵
    0.06
    텐
    0.06
    λου
    0.06
     reliable
    0.06
    Act Density 0.002%

    No Known Activations