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

    Neuronpedia

    INDEX
    Explanations

    emphasis markers or formatting indicators in the text

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

    bolded numbers and letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.51
     linkovi
    -0.47
    enderror
    -0.46
    -0.46
    MigrationBuilder
    -0.46
    guenos
    -0.45
    sizeCache
    -0.45
    Билгалдахарш
    -0.45
    __':
    -0.44
    __":
    -0.43
    POSITIVE LOGITS
    <strong>
    0.84
    <em>
    0.50
    ſelves
    0.48
    PositiveButton
    0.45
     dezelve
    0.45
    Bertrand
    0.41
    <sup>
    0.41
    rejo
    0.40
    </strong>
    0.40
     artific
    0.40
    Act Density 0.019%

    No Known Activations