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

    Neuronpedia

    INDEX
    Explanations

    instances of high-frequency content, indicating significant activities or emphasis in the text

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

    foreign language or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     this
    -0.34
     This
    -0.31
    This
    -0.30
     Co
    -0.29
    ↵↵↵
    -0.28
    <eos>
    -0.28
     what
    -0.26
     Du
    -0.26
     onSave
    -0.24
     Mu
    -0.24
    POSITIVE LOGITS
     otomatig
    0.98
     Савезне
    0.93
    ########.
    0.88
     surla
    0.77
     Мексичка
    0.76
    verwijspagina
    0.76
     للمعارف
    0.75
     queſta
    0.75
    Rhestr
    0.73
    IndentedString
    0.73
    Act Density 0.449%

    No Known Activations