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

    Neuronpedia

    INDEX
    Explanations

    prominent names or references in a document

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

    author names and roles

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of personal names, particularly author names in metadata or text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ênis
    -0.44
    رشف
    -0.44
    تقاوى
    -0.37
     beteken
    -0.37
     entanto
    -0.37
     prochaine
    -0.36
     snippetHide
    -0.36
    Gemeinden
    -0.36
     autrement
    -0.35
     muchísimo
    -0.35
    POSITIVE LOGITS
     AssemblyCompany
    0.66
     يتيمه
    0.59
    ❋
    0.56
     Chief
    0.55
    DockStyle
    0.54
    évaluateur
    0.54
     author
    0.54
     createState
    0.53
    OGND
    0.51
    IUrlHelper
    0.51
    Act Density 0.002%

    No Known Activations