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

    Neuronpedia

    INDEX
    Explanations

    references to language and linguistic proficiency

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

    references and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.40
     OFDb
    -0.39
    SBATCH
    -0.38
     boîtier
    -0.38
     nôtre
    -0.38
     jouet
    -0.38
     Moscú
    -0.37
    ViewImports
    -0.36
     extranjera
    -0.36
     okuyayım
    -0.35
    POSITIVE LOGITS
    脚注の使い方
    0.55
     mahar
    0.50
    Sno
    0.46
    口
    0.45
     percep
    0.45
     Chandigarh
    0.45
    thâu
    0.45
    ensible
    0.45
     للاسماء
    0.45
    IGraphics
    0.44
    Act Density 0.037%

    No Known Activations