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

    Neuronpedia

    INDEX
    Explanations

    passive constructions and forms of the verb "to be."

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

    all followed by verb/adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sometimes
    -0.40
     parfois
    -0.39
     acer
    -0.36
     voire
    -0.35
    Sometimes
    -0.35
     TV
    -0.34
     talvez
    -0.34
    rmse
    -0.34
    HttpGet
    -0.33
    viewPager
    -0.33
    POSITIVE LOGITS
     defaultstate
    0.82
     Semua
    0.71
     ویکی‌پدی
    0.68
    Sucesor
    0.66
     '\\;'
    0.66
    abestanden
    0.64
    WriteBarrier
    0.63
     Wszyst
    0.63
     Wikimedijinoj
    0.60
     All
    0.60
    Act Density 0.066%

    No Known Activations