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

    Neuronpedia

    INDEX
    Explanations

    keywords associated with programming constructs and data structures

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

    code statement terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <pad>
    -0.69
    <unused28>
    -0.69
    <unused3>
    -0.69
    [@BOS@]
    -0.69
    -0.69
     Dieſe
    -0.69
    <unused16>
    -0.68
    <unused41>
    -0.68
    <unused14>
    -0.68
    <unused8>
    -0.68
    POSITIVE LOGITS
    en
    0.32
    CDCl
    0.31
    er
    0.31
    be
    0.29
     along
    0.28
    EN
    0.28
    iro
    0.28
    as
    0.28
    id
    0.27
    nahme
    0.27
    Act Density 0.014%

    No Known Activations