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

    Neuronpedia

    INDEX
    Explanations

    references to personal backgrounds and origins

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

    Location or origin after "from" or "in"

    np_acts-logits-general · gemini-2.0-flash

    place names after "from" or "in"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.74
    ModelSerializer
    -0.68
    FailureListener
    -0.62
    createServer
    -0.60
    PreferredItem
    -0.57
     <=",
    -0.57
    ']))
    -0.56
     Lordships
    -0.55
     HttpNotFound
    -0.55
    itinéraire
    -0.54
    POSITIVE LOGITS
    mutate
    0.57
    émica
    0.53
    OfBirth
    0.53
    ylation
    0.53
     виправивши
    0.53
    habits
    0.52
     whom
    0.50
     beaten
    0.50
    μένη
    0.50
     Eastern
    0.50
    Act Density 0.176%

    No Known Activations