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

    Neuronpedia

    INDEX
    Explanations

    quantifiable metrics or data related to scientific research

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

    scientific articles, preprints, and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.75
     propOrder
    -0.69
    Personensuche
    -0.66
    存于互联网档案馆
    -0.63
    ſehen
    -0.63
    featureID
    -0.62
    Parcelize
    -0.60
    twimg
    -0.59
    SpringRunner
    -0.58
    ngdoc
    -0.58
    POSITIVE LOGITS
     affaires
    0.35
    hamilan
    0.32
     Affaires
    0.32
    ImageName
    0.30
    ביוגרפיה
    0.30
    itados
    0.29
    bleib
    0.29
     Silber
    0.29
     grom
    0.28
    withOpacity
    0.28
    Act Density 0.234%

    No Known Activations