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

    Neuronpedia

    INDEX
    Explanations

    references to the global population and worldwide issues

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

    global context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.43
    exitRule
    -0.38
     Lenny
    -0.37
    expandindo
    -0.36
    aarrggbb
    -0.36
     CURIAM
    -0.36
    шру
    -0.35
    unca
    -0.35
    الحياه
    -0.35
    Bienvenue
    -0.34
    POSITIVE LOGITS
     world
    0.81
    world
    0.66
     worldwide
    0.64
     dünya
    0.63
     wereld
    0.63
     värld
    0.63
    WORLD
    0.63
     mundiales
    0.63
     dunia
    0.61
     WORLD
    0.61
    Act Density 0.032%

    No Known Activations