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

    Neuronpedia

    INDEX
    Explanations

    the phrase "in [time period]" indicating occurrences or events over specific durations

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

    first time / first number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dağı
    -0.32
     deseos
    -0.31
     выделя
    -0.30
    occupe
    -0.30
    🔀
    -0.29
    endroit
    -0.28
    include
    -0.28
     junto
    -0.28
     also
    -0.28
     oscuridad
    -0.28
    POSITIVE LOGITS
     ſind
    0.69
    uxxxx
    0.66
     Chwiliwch
    0.66
     Verſ
    0.66
     myſelf
    0.65
    Хьажоргаш
    0.65
     Monfieur
    0.64
     geſch
    0.63
     Мексичка
    0.62
     ſeveral
    0.62
    Act Density 0.016%

    No Known Activations