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

    Neuronpedia

    INDEX
    Explanations

    punctuation and syntax elements in programming or markup code

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

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused79>
    -1.22
    <unused41>
    -1.22
    <pad>
    -1.21
    [@BOS@]
    -1.21
    <unused43>
    -1.21
    <unused52>
    -1.21
    <unused28>
    -1.21
    <unused23>
    -1.21
    <unused14>
    -1.21
    <unused16>
    -1.21
    POSITIVE LOGITS
    .
    0.70
    ↵↵
    0.70
    ↵
    0.56
    2
    0.56
    The
    0.52
    ↵↵↵
    0.49
     
    0.49
    3
    0.49
    1
    0.47
    A
    0.46
    Act Density 0.018%

    No Known Activations