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

    Neuronpedia

    INDEX
    Explanations

    references to decoding processes or functions in programming contexts

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

    decoder, decode, decoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yit
    -0.50
    WriteLiteral
    -0.49
    gemini
    -0.45
    ⎡
    -0.45
    তথ্যসূত্র
    -0.45
    '][]
    -0.44
    ########.
    -0.44
    y
    -0.44
    <![
    -0.44
    Stanley
    -0.43
    POSITIVE LOGITS
    Decoder
    2.72
     Decoder
    2.25
    decoder
    2.23
     decoder
    2.17
     decoding
    1.07
     deco
    1.05
    decode
    1.05
    解码
    0.92
    Decode
    0.91
     decode
    0.89
    Act Density 0.006%

    No Known Activations