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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures and programming constructs in code

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

    code and programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.37
     very
    -0.32
    --
    -0.32
    LogFactory
    -0.31
    1
    -0.29
    ↵↵
    -0.29
    at
    -0.29
    </blockquote>
    -0.28
    up
    -0.28
     since
    -0.28
    POSITIVE LOGITS
     يتيمه
    0.81
     EconPapers
    0.80
     تضيفلها
    0.75
    <unused3>
    0.69
    [@BOS@]
    0.68
    <unused28>
    0.68
    <unused41>
    0.68
    <unused17>
    0.68
    <unused8>
    0.68
    <unused14>
    0.68
    Act Density 0.017%

    No Known Activations