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

    Neuronpedia

    INDEX
    Explanations

    topics related to personal relationships and familial connections

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

    after commas and periods

    np_acts-logits-general · gemini-2.0-flash

    discussion topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.81
    featureID
    -0.79
     Normdatei
    -0.76
     Anſ
    -0.73
     CreateTagHelper
    -0.70
    <unused14>
    -0.66
    <unused51>
    -0.65
    <unused41>
    -0.65
    <unused28>
    -0.65
    [@BOS@]
    -0.65
    POSITIVE LOGITS
     issues
    0.54
     matters
    0.49
     topics
    0.48
     topic
    0.46
     details
    0.41
     TOPICS
    0.39
     ISSUES
    0.38
     issue
    0.35
    bibitem
    0.35
     specifics
    0.35
    Act Density 0.532%

    No Known Activations