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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robes
    -0.07
    =Y
    -0.06
    ансов
    -0.06
    rede
    -0.06
    َي
    -0.06
    emony
    -0.06
    erty
    -0.06
    lical
    -0.06
    στηκε
    -0.06
     robe
    -0.06
    POSITIVE LOGITS
    Absolutely
    0.07
     maximizing
    0.06
     GroupLayout
    0.06
    .Second
    0.06
     f
    0.06
    useState
    0.06
     Negative
    0.06
     Hanson
    0.06
    0.06
    變
    0.06
    Act Density 0.003%

    No Known Activations