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

    Neuronpedia

    INDEX
    Explanations

    the repetitive use of the phrase "É" and its variations in the context of defining players or scores

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

    states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.76
    脚注の使い方
    -0.73
     surla
    -0.70
     يتيمه
    -0.67
     ujednoznacz
    -0.65
    parsedMessage
    -0.63
    yarnpkg
    -0.62
    SharedDtor
    -0.61
    Diweddarwch
    -0.61
    rrggbb
    -0.60
    POSITIVE LOGITS
     is
    0.71
    ίναι
    0.69
     está
    0.48
     είναι
    0.48
    Está
    0.48
     وهو
    0.47
     Is
    0.47
     Está
    0.46
     was
    0.46
     เป็น
    0.45
    Act Density 0.011%

    No Known Activations