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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the introduction or progression of content in discussions or narratives

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

    introducing a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.94
     للمعارف
    -0.94
    IUrlHelper
    -0.86
     Normdatei
    -0.81
    niſſe
    -0.79
     EconPapers
    -0.79
     يتيمه
    -0.77
     kasarigan
    -0.76
    verwijspagina
    -0.76
     виправивши
    -0.76
    POSITIVE LOGITS
     begins
    0.34
     start
    0.34
     initComponents
    0.33
    !
    0.33
    .
    0.31
     Söz
    0.31
    OPER
    0.31
     operations
    0.31
    ↵
    0.30
     &
    0.29
    Act Density 0.011%

    No Known Activations