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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific components and organizational structures

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

    parts and divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.53
    ↵
    -0.45
    1
    -0.43
     and
    -0.42
    2
    -0.41
     as
    -0.41
     ever
    -0.41
     very
    -0.41
     is
    -0.41
      
    -0.39
    POSITIVE LOGITS
    parsedMessage
    0.89
    MigrationBuilder
    0.86
    <unused52>
    0.81
     Geſch
    0.81
    <unused74>
    0.80
    <unused47>
    0.80
     ویکی‌پدی
    0.80
    <unused14>
    0.80
    [@BOS@]
    0.79
    <unused8>
    0.79
    Act Density 0.151%

    No Known Activations