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

    Neuronpedia

    INDEX
    Explanations

    references to authorship and manuscript preparation

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

    manuscript discussing content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.73
     '\\;'
    -0.59
    GEBURTSDATUM
    -0.58
     للاسماء
    -0.58
     ویکی‌آمباردا
    -0.57
     Савезне
    -0.55
    routeProvider
    -0.54
     configureStore
    -0.54
    Cyfeiriadau
    -0.53
     iprot
    -0.53
    POSITIVE LOGITS
     désolés
    0.38
     draft
    0.36
    esség
    0.36
     manuscript
    0.35
    FileVersion
    0.34
     revised
    0.33
     drafts
    0.33
     Draft
    0.32
    FormTagHelper
    0.31
     manuscrit
    0.31
    Act Density 0.007%

    No Known Activations