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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and events

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

    historical figures and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shock
    -0.49
    トーク
    -0.47
    NameInMap
    -0.47
    verwijspagina
    -0.46
    mnar
    -0.44
     feed
    -0.43
    TRIBUN
    -0.43
     briefing
    -0.43
     ط
    -0.42
     browsing
    -0.42
    POSITIVE LOGITS
     procès
    0.50
     ſch
    0.45
     pleaſure
    0.44
     juſ
    0.43
     Picchu
    0.43
     himſelf
    0.43
     ſtre
    0.43
    ſelf
    0.42
     spiritu
    0.42
     itſelf
    0.42
    Act Density 0.034%

    No Known Activations