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

    Neuronpedia

    INDEX
    Explanations

    long short-term memory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    日渐
    -0.07
    (yy
    -0.07
     ----------------------------------------------------------------------------↵
    -0.07
     yy
    -0.06
    越是
    -0.06
    🕚
    -0.06
    ?',↵
    -0.06
    짦
    -0.06
     so
    -0.06
     Dmitry
    -0.06
    POSITIVE LOGITS
    CollectionView
    0.07
     אה
    0.07
    Station
    0.07
    うち
    0.07
     ambush
    0.07
    休息
    0.07
    testing
    0.06
     Castillo
    0.06
    ていきたい
    0.06
     Expansion
    0.06
    Act Density 0.002%

    No Known Activations