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

    Neuronpedia

    INDEX
    Explanations

    references to contrasts between light and darkness

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

    darkness, night, or grey areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anſ
    -0.60
     preſent
    -0.57
     leſs
    -0.57
     kasarigan
    -0.55
     myſelf
    -0.54
     itſelf
    -0.52
     Jefus
    -0.52
     ſind
    -0.51
    Diweddarwch
    -0.50
     ſta
    -0.49
    POSITIVE LOGITS
    NameValuePair
    0.37
     night
    0.33
    ắm
    0.31
     Vrbo
    0.30
    initializeApp
    0.30
     begs
    0.29
    UnsafeEnabled
    0.28
    AddHtmlAttribute
    0.28
    ępo
    0.28
    Personensuche
    0.28
    Act Density 0.086%

    No Known Activations