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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or structural elements in the text

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

    the presence of the beginning of a new segment or block of text, often marked by specific tokens

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

    barbadensis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ContentAsync
    -0.56
     Basque
    -0.53
    chengladbach
    -0.53
    ParallelGroup
    -0.52
    =$?
    -0.52
     Patagonia
    -0.51
    kiye
    -0.50
    istocene
    -0.50
     Sverige
    -0.50
     Мексичка
    -0.50
    POSITIVE LOGITS
    ChildIndex
    0.60
    let
    0.55
    št
    0.51
    hurt
    0.49
     slik
    0.49
     papai
    0.49
    /*:
    0.49
     št
    0.49
    (<
    0.48
    artem
    0.48
    Act Density 0.039%

    No Known Activations