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

    Neuronpedia

    INDEX
    Explanations

    references to publications and academic documents

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

    citation page numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mkdirs
    -0.33
    ala
    -0.33
     Sach
    -0.32
     run
    -0.31
     barra
    -0.31
    aussian
    -0.30
     gir
    -0.30
    simpleType
    -0.30
     gel
    -0.30
     ++
    -0.30
    POSITIVE LOGITS
    AsUp
    0.77
     فريبيس
    0.71
     esternos
    0.63
     gyhoeddwyd
    0.63
    DockStyle
    0.63
    webElementXpaths
    0.62
    XmlAccessorType
    0.61
    цездатний
    0.60
    PreferredItem
    0.60
    itinéraire
    0.59
    Act Density 0.001%

    No Known Activations