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

    Neuronpedia

    INDEX
    Explanations

    database-related operations and structures

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

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stand
    -0.44
     Stol
    -0.40
     STAND
    -0.40
     Stand
    -0.38
     sign
    -0.38
    회
    -0.37
     Ale
    -0.36
     Singer
    -0.36
     사이
    -0.36
     gra
    -0.35
    POSITIVE LOGITS
     informée
    0.75
     ویکی‌پدیا
    0.69
    WriteTagHelper
    0.67
     '\\;'
    0.63
    setVerticalGroup
    0.63
    IndentedString
    0.62
     Perſ
    0.62
     Италијани
    0.60
     <>",
    0.60
     Anſ
    0.60
    Act Density 0.001%

    No Known Activations