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

    Neuronpedia

    INDEX
    Explanations

    references to alphanumeric characters and their combinations

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

    letters and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aDecoder
    -0.51
     generality
    -0.37
    然
    -0.35
     Ethical
    -0.34
     trouw
    -0.34
    matchCondition
    -0.34
     GAO
    -0.34
    AUTHOR
    -0.33
     Holm
    -0.33
     helft
    -0.33
    POSITIVE LOGITS
    phanumeric
    0.93
    UVWXYZ
    0.88
    qrstuvwxyz
    0.69
    rawDesc
    0.65
    isalpha
    0.63
    verifyException
    0.60
     AssemblyCompany
    0.59
    المناصب
    0.48
    RectangleBorder
    0.47
    DrawerToggle
    0.47
    Act Density 0.041%

    No Known Activations