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

    Neuronpedia

    INDEX
    Explanations

    updates and improvements related to software features

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

    improvements and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.71
    RectangleBorder
    -0.57
    URLException
    -0.52
     Paglinawan
    -0.52
     AssemblyCompany
    -0.51
    RegistryLite
    -0.50
    tagext
    -0.49
    NamedQuery
    -0.47
     disambiguazione
    -0.47
     psicológico
    -0.46
    POSITIVE LOGITS
     new
    0.45
     المعيارى
    0.40
    .='
    0.39
     Trips
    0.38
    립
    0.38
     dAtA
    0.37
     nuovo
    0.37
    fieras
    0.37
     improvements
    0.37
     improved
    0.37
    Act Density 0.013%

    No Known Activations