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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter 'e' in various contexts within code snippets

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     newBuilder
    -0.75
     BoxFit
    -0.71
    mpagne
    -0.70
     }{@
    -0.69
     AssemblyCompany
    -0.69
     JpaRepository
    -0.68
    principalTable
    -0.68
    <unused14>
    -0.68
    [@BOS@]
    -0.68
    <unused8>
    -0.68
    POSITIVE LOGITS
    e
    0.40
    preventDefault
    0.32
    splitContainer
    0.30
    tr
    0.28
     stop
    0.27
    beginPath
    0.27
    στά
    0.27
    …
    0.27
    i
    0.27
    SneakyThrows
    0.26
    Act Density 0.002%

    No Known Activations