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

    Neuronpedia

    INDEX
    Explanations

    pieces of code or programming-related syntax

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

    diverse tokens in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gruesa
    -0.21
     altid
    -0.20
     vigueur
    -0.20
     Kindheit
    -0.19
     właśnie
    -0.19
     orgullo
    -0.19
     tzw
    -0.19
     sanguí
    -0.18
     urbaine
    -0.17
     همیشه
    -0.17
    POSITIVE LOGITS
     ſeyn
    1.13
     パンチラ
    1.13
    ſelben
    1.13
     geweſen
    1.12
    iſche
    1.12
     Dieſe
    1.10
    <unused14>
    1.09
    <unused16>
    1.09
    <unused1>
    1.09
    [@BOS@]
    1.09
    Act Density 0.033%

    No Known Activations