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

    Neuronpedia

    INDEX
    Explanations

    conversational connectors and transition words

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

    fact confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.57
     noDo
    -0.42
    Diweddarwch
    -0.38
     يتيمه
    -0.38
     меда
    -0.35
     nonUne
    -0.35
    віду
    -0.34
    عرِّف
    -0.34
     dece
    -0.33
    Ziel
    -0.33
    POSITIVE LOGITS
     altså
    0.75
     bowiem
    0.72
     totiž
    0.71
     alltså
    0.68
     nemlig
    0.68
    brigens
    0.66
     appunto
    0.65
     eben
    0.65
    AddTagHelper
    0.62
     przecież
    0.62
    Act Density 0.013%

    No Known Activations