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

    Neuronpedia

    INDEX
    Explanations

    references to specific games and gaming experiences

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

    game, tracking, sorting, card monte

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entera
    -0.29
    ーズ
    -0.29
     estat
    -0.28
     stanovnika
    -0.28
     comodidad
    -0.28
    ↵↵
    -0.28
     ignored
    -0.28
     Kriege
    -0.27
    2
    -0.27
     eredmény
    -0.27
    POSITIVE LOGITS
    transQ
    0.83
     للمعارف
    0.75
    <unused28>
    0.69
    <unused23>
    0.69
    <unused41>
    0.69
    <unused79>
    0.69
    ロウィン
    0.69
    Tikang
    0.69
    <unused3>
    0.69
    <unused14>
    0.69
    Act Density 0.024%

    No Known Activations