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

    Neuronpedia

    INDEX
    Explanations

    11

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wert
    -0.07
    Constructed
    -0.07
     погод
    -0.07
    adows
    -0.06
    :k
    -0.06
     pigs
    -0.06
    ulur
    -0.06
    iê
    -0.06
     HC
    -0.06
     Wig
    -0.06
    POSITIVE LOGITS
     reassure
    0.08
    가격
    0.06
     customers
    0.06
    fallback
    0.06
    人民共和国
    0.06
     сов
    0.06
    listed
    0.06
    $conn
    0.06
    ÔNG
    0.06
     rửa
    0.06
    Act Density 0.001%

    No Known Activations