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

    Neuronpedia

    INDEX
    Explanations

    references to physical spaces and boundaries

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

    places and boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.66
    ftagPool
    -0.59
    endphp
    -0.58
    NameInMap
    -0.57
    pecabe
    -0.57
     &___
    -0.56
     '\\;'
    -0.56
    :✨
    -0.56
    AddTagHelper
    -0.55
     CreateTagHelper
    -0.54
    POSITIVE LOGITS
     comp
    0.36
     страницы
    0.31
    withIdentifier
    0.31
     strå
    0.30
    helves
    0.29
     ooit
    0.29
     стены
    0.29
     قاب
    0.28
     pom
    0.28
     pages
    0.28
    Act Density 0.061%

    No Known Activations