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

    Neuronpedia

    INDEX
    Explanations

    complex multi-word sequences or phrases

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

    study durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kam
    -0.41
     te
    -0.38
    WriteTagHelper
    -0.37
    WebElementEntity
    -0.37
     “
    -0.37
     Kam
    -0.37
    fattning
    -0.36
     Stur
    -0.35
     blu
    -0.34
    й
    -0.34
    POSITIVE LOGITS
    tagHelperRunner
    0.65
    Попис
    0.57
     autorytatywna
    0.57
     Económica
    0.55
     '\\;'
    0.55
    lihatan
    0.53
     enfans
    0.53
     AssemblyCompany
    0.53
    +#+#
    0.53
     JpaRepository
    0.52
    Act Density 0.091%

    No Known Activations