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

    Neuronpedia

    INDEX
    Explanations

    sections related to study methodology and experimental design

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

    Section titles: "Background", "Methods", or "Results"

    np_acts-logits-general · gemini-2.0-flash

    section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused14>
    -1.04
    <unused16>
    -1.03
    <unused41>
    -1.03
    <unused79>
    -1.03
    <unused28>
    -1.03
    <unused3>
    -1.03
    <unused51>
    -1.03
    <unused52>
    -1.03
    <pad>
    -1.02
    [@BOS@]
    -1.02
    POSITIVE LOGITS
    :
    0.47
    ↵↵
    0.39
    </strong>
    0.35
    ;
    0.34
    ↵
    0.34
    ładka
    0.31
    ?
    0.31
    </h3>
    0.30
     Features
    0.30
    </em>
    0.29
    Act Density 0.290%

    No Known Activations