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

    Neuronpedia

    INDEX
    Explanations

    references to countries and regions

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

    countries and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hentet
    -0.51
    AndEndTag
    -0.47
     esternos
    -0.45
    TypedDataSet
    -0.45
    ViewImports
    -0.43
    AsUp
    -0.43
    Карьера
    -0.42
    Personendaten
    -0.40
     HasFactory
    -0.40
    uxxxx
    -0.39
    POSITIVE LOGITS
     pathologies
    0.45
     nations
    0.45
     constituencies
    0.44
     counties
    0.43
     creeds
    0.42
     kingdoms
    0.41
    $^\
    0.41
    strijden
    0.41
     designations
    0.40
    ❹
    0.40
    Act Density 0.053%

    No Known Activations