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

    Neuronpedia

    INDEX
    Explanations

    key phrases and terms related to systems, organization, and support structures in various contexts

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

    near modern, essentially works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.77
    تقاوى
    -0.61
     kasarigan
    -0.60
     queſta
    -0.52
     OFDb
    -0.52
     ParseException
    -0.50
    sidemargin
    -0.50
    adaptiveStyles
    -0.50
     للمعارف
    -0.49
     estekak
    -0.48
    POSITIVE LOGITS
    AddTagHelper
    0.51
    WriteTagHelper
    0.44
    appro
    0.36
     CreateTagHelper
    0.35
     sk
    0.35
     intelig
    0.35
    الدراسه
    0.34
    thing
    0.34
     pro
    0.33
    kloped
    0.33
    Act Density 0.048%

    No Known Activations