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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to ideas and their significance

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

    proposing ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ChromeDriver
    -0.45
     elég
    -0.44
     arquitecto
    -0.40
     governador
    -0.40
     Congrès
    -0.39
    ChromeDriver
    -0.39
     évêque
    -0.39
     diseñador
    -0.37
    PasswordEncoder
    -0.37
     parachoque
    -0.36
    POSITIVE LOGITS
     Concept
    0.69
     ModelExpression
    0.66
     CONCEPT
    0.66
    Concept
    0.64
     concept
    0.63
    concept
    0.62
    Personendaten
    0.61
     Concepts
    0.56
     notion
    0.54
     Idea
    0.53
    Act Density 0.009%

    No Known Activations