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

    Neuronpedia

    INDEX
    Explanations

    references to elements related to programming and digital components

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

    code structures with elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.93
     AssemblyTitle
    -0.85
    存于互联网档案馆
    -0.75
    ngdoc
    -0.71
     '{@
    -0.70
     lenker
    -0.69
    ')),
    -0.69
    ftagPool
    -0.69
    extAlignment
    -0.68
    ")))
    -0.67
    POSITIVE LOGITS
     enfans
    0.38
    ñora
    0.36
     ángel
    0.33
     Moscú
    0.33
    gjenge
    0.32
    namientos
    0.32
    énage
    0.32
     maleta
    0.31
     señores
    0.31
     språk
    0.30
    Act Density 0.014%

    No Known Activations