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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "legend" and its variants

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

    legends and myths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    housie
    -0.48
    Riverside
    -0.48
     Middlesbrough
    -0.47
     Riverside
    -0.47
     Niro
    -0.46
    jmniej
    -0.44
     Sarkozy
    -0.44
    Ufficio
    -0.42
    Autowired
    -0.42
     Whirlpool
    -0.42
    POSITIVE LOGITS
     Legend
    2.03
     legend
    1.92
    Legend
    1.89
    legend
    1.77
     LEGEND
    1.75
     legends
    1.66
     Legends
    1.56
    LEGEND
    1.48
     légende
    1.46
     leyenda
    1.45
    Act Density 0.005%

    No Known Activations