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

    Neuronpedia

    INDEX
    Explanations

    references to upcoming sections or discussions in a text

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

    next section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ParallelGroup
    -0.76
     мәкал
    -0.65
    ♼
    -0.62
    utilisons
    -0.61
    MessageOf
    -0.59
    Personendaten
    -0.57
     AssemblyCompany
    -0.56
    AddTagHelper
    -0.56
    lapsingToolbar
    -0.56
    IUrlHelper
    -0.53
    POSITIVE LOGITS
     tomorrow
    0.46
     future
    0.42
     next
    0.41
     nästa
    0.41
     demain
    0.40
    SuspendLayout
    0.39
     initComponents
    0.39
    morrow
    0.37
    future
    0.37
    oflavin
    0.37
    Act Density 0.064%

    No Known Activations