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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases indicating capacity or fullness

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

    full or booked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :+:
    -0.56
    ysuckle
    -0.46
     pinulongan
    -0.45
    IDL
    -0.45
     rhestr
    -0.45
     للمعارف
    -0.44
     Италијани
    -0.44
    ۣ
    -0.44
    MIDDLEWARE
    -0.43
     wikipagina
    -0.43
    POSITIVE LOGITS
     filled
    0.68
     запол
    0.61
     Filled
    0.60
    Filled
    0.60
    filled
    0.59
     fill
    0.59
     filling
    0.57
     fills
    0.56
    滿
    0.56
     rempli
    0.56
    Act Density 0.081%

    No Known Activations