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

    Neuronpedia

    INDEX
    Explanations

    terms related to global prominence and leadership

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

    Superlatives like "largest," "biggest," or "first."

    np_acts-logits-general · gemini-2.0-flash

    world's largest, biggest, first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     either
    -0.41
     Rinse
    -0.41
     Hahn
    -0.38
    Rinse
    -0.36
     or
    -0.35
    warted
    -0.35
     Lacy
    -0.35
     penultimate
    -0.34
     butcher
    -0.34
    ])->
    -0.34
    POSITIVE LOGITS
     world
    1.48
    world
    1.27
     WORLD
    1.16
     wereld
    1.13
    World
    1.08
     dunia
    1.08
    WORLD
    1.07
    世界
    1.07
     World
    1.05
     mundo
    1.04
    Act Density 0.131%

    No Known Activations