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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structure in code snippets

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

    multilingual code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pektrum
    -0.34
     velours
    -0.33
     persil
    -0.32
     both
    -0.30
     invokingState
    -0.29
     matka
    -0.29
    ViewImports
    -0.28
     Wiktionnaire
    -0.28
    väl
    -0.28
     feed
    -0.28
    POSITIVE LOGITS
     Wikimedijinoj
    0.66
    хьтан
    0.65
     surla
    0.62
     nakalista
    0.58
     dAtA
    0.57
    Хьажоргаш
    0.57
     Austen
    0.56
    Personensuche
    0.56
    лтемелер
    0.55
     ivelany
    0.55
    Act Density 0.513%

    No Known Activations