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

    Neuronpedia

    INDEX
    Explanations

    retirement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bubble
    -0.07
     obvious
    -0.07
     товарів
    -0.07
    ません
    -0.07
     humanitarian
    -0.06
     asserted
    -0.06
     مسیر
    -0.06
     reaction
    -0.06
     identified
    -0.06
     accommodations
    -0.06
    POSITIVE LOGITS
    otty
    0.07
     retirement
    0.07
    pecia
    0.06
    enci
    0.06
     ledna
    0.06
    spb
    0.06
    řad
    0.06
    ilight
    0.06
    fr
    0.06
    .Stop
    0.06
    Act Density 0.003%

    No Known Activations