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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names, indicating individuals and their identities

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

    end_of_turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     micro
    -0.32
     viewDidLoad
    -0.29
     stores
    -0.28
     Bullock
    -0.28
     pile
    -0.28
    兵
    -0.27
    UNO
    -0.27
     を
    -0.26
     re
    -0.26
     pubs
    -0.26
    POSITIVE LOGITS
    rungsseite
    0.85
     intptr
    0.78
    AddTagHelper
    0.75
     ujednoznacz
    0.75
     autorytatywna
    0.72
    OGND
    0.71
    addCriterion
    0.66
     gynnwys
    0.66
     betweenstory
    0.66
    LabelTagHelper
    0.65
    Act Density 0.073%

    No Known Activations