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

    Neuronpedia

    INDEX
    Explanations

    references to problems or issues related to social dynamics and historical context

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

    introducing a specific item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.70
     estimés
    -0.62
    Enllaces
    -0.60
     initComponents
    -0.59
    ValueStyle
    -0.57
    zionalità
    -0.57
    RefNanny
    -0.56
    Geplaatst
    -0.54
    oprot
    -0.54
    يميديا
    -0.54
    POSITIVE LOGITS
     another
    0.78
    Еще
    0.61
     something
    0.57
    UserScript
    0.57
     otro
    0.57
     getItemId
    0.57
     special
    0.57
    another
    0.56
    itemBuilder
    0.56
     problem
    0.54
    Act Density 0.159%

    No Known Activations