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

    Neuronpedia

    INDEX
    Explanations

    names of prominent individuals and their affiliations

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

    German surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Spra
    -0.54
     Nieren
    -0.50
    ActionCreators
    -0.48
    reportWebVitals
    -0.48
    PerformLayout
    -0.47
    Obfuscated
    -0.45
    OUGH
    -0.45
     Monfieur
    -0.45
    scalatest
    -0.45
    Šaltiniai
    -0.44
    POSITIVE LOGITS
     становника
    0.45
     şirket
    0.39
    toli
    0.36
    SpringRunner
    0.35
     Secretariat
    0.35
    kheim
    0.34
    Mayer
    0.34
    躇
    0.33
    abbix
    0.33
    Кита
    0.33
    Act Density 0.246%

    No Known Activations