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

    Neuronpedia

    INDEX
    Explanations

    procedural and structural elements in technical documents

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

    list item identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niſſe
    -0.91
    存于互联网档案馆
    -0.89
    majánló
    -0.88
     ſeinen
    -0.87
    iſchen
    -0.87
    <unused52>
    -0.87
    <unused14>
    -0.87
    <unused23>
    -0.86
    <unused16>
    -0.86
    <unused8>
    -0.86
    POSITIVE LOGITS
     the
    0.38
     The
    0.37
     is
    0.35
     
    0.34
    com
    0.34
    The
    0.33
    l
    0.33
    of
    0.33
     =
    0.33
     All
    0.32
    Act Density 0.021%

    No Known Activations