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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to engineering and mechanical processes

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

    thin, small objects/parts

    np_acts-logits-general · gemini-2.0-flash

    describing physical components and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -1.09
     cherchés
    -0.93
     autorytatywna
    -0.91
    setVerticalGroup
    -0.90
    出版年
    -0.87
    rrggbb
    -0.87
    fromnode
    -0.86
     المعيارى
    -0.86
    Personendaten
    -0.86
    ⓧ
    -0.85
    POSITIVE LOGITS
     ed
    0.53
     white
    0.50
     small
    0.47
     another
    0.46
    міністра
    0.45
     a
    0.45
     fixé
    0.45
     additional
    0.44
     cố
    0.44
     series
    0.44
    Act Density 0.831%

    No Known Activations