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

    Neuronpedia

    INDEX
    Explanations

    references to the reader or viewer's experience and engagement with the text

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

    referring the reader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.41
     Numerade
    -0.41
     potret
    -0.41
    umoj
    -0.40
    champion
    -0.40
    Condol
    -0.40
     esimerkiksi
    -0.40
     vantaggio
    -0.40
     histórica
    -0.39
    Champion
    -0.38
    POSITIVE LOGITS
     snippetHide
    0.57
     aDecoder
    0.53
     CURIAM
    0.52
    참고
    0.48
    IonicModule
    0.46
    MessageTagHelper
    0.45
     пользователя
    0.45
     reader
    0.45
     пользователем
    0.44
     createState
    0.44
    Act Density 0.075%

    No Known Activations