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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation typically used in programming or markup languages

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

    user mathematical queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused28>
    -1.02
    <unused14>
    -1.02
    [@BOS@]
    -1.02
    <unused8>
    -1.02
    <unused47>
    -1.02
    <unused23>
    -1.02
    <unused43>
    -1.02
    <unused41>
    -1.02
    <unused16>
    -1.02
    <unused17>
    -1.02
    POSITIVE LOGITS
    testng
    0.68
    getTest
    0.36
    .
    0.32
    ,
    0.30
     version
    0.28
     test
    0.28
     analysis
    0.26
     T
    0.26
    ↵↵
    0.25
     Day
    0.24
    Act Density 0.000%

    No Known Activations