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

    Neuronpedia

    INDEX
    Explanations

    issues related to performance inefficiencies in systems and processes

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

    Follows words indicating difficulties or improvements

    np_acts-logits-general · gemini-2.0-flash

    problems and improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThemeOverlay
    -0.46
     futur
    -0.40
    agree
    -0.37
    ough
    -0.36
    adem
    -0.36
    学
    -0.36
     Piac
    -0.35
     estre
    -0.35
    系
    -0.34
    rega
    -0.34
    POSITIVE LOGITS
    SequentialGroup
    0.59
    sizeCache
    0.48
     pinulongan
    0.47
    Diweddarwch
    0.46
     AssemblyCompany
    0.46
    IsContent
    0.46
    +#+#
    0.46
    ftagPool
    0.45
    تفصیلات
    0.44
    muerzo
    0.43
    Act Density 0.553%

    No Known Activations