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

    Neuronpedia

    INDEX
    Explanations

    specific types or classifications of variables and parameters

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

    citations and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    -0.52
    in
    -0.45
    w
    -0.43
    ak
    -0.41
    is
    -0.40
    v
    -0.40
    ا
    -0.40
    ad
    -0.40
    ो
    -0.39
    un
    -0.39
    POSITIVE LOGITS
    parsedMessage
    0.90
    SharedCtor
    0.77
    featureID
    0.76
     gyhoeddwyd
    0.72
     queſta
    0.72
    transQ
    0.69
    KommentareTeilen
    0.67
    oredCriteria
    0.65
    utilisons
    0.63
     pleaſure
    0.63
    Act Density 0.300%

    No Known Activations