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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or acknowledgement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    immunosuppressive or Japanese sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.52
    WebServlet
    -0.50
    openqa
    -0.50
    }{*}{
    -0.44
     Bav
    -0.44
     veto
    -0.44
    Forecast
    -0.43
    !*\
    -0.43
    Scout
    -0.43
    Trail
    -0.43
    POSITIVE LOGITS
    mektedir
    1.06
    melidir
    0.96
    miştir
    0.96
    하였다
    0.93
    maktadır
    0.90
    mıştır
    0.77
    ılmıştır
    0.76
     olacaktır
    0.73
    cektir
    0.70
    malıdır
    0.70
    Act Density 0.002%

    No Known Activations