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

    Neuronpedia

    INDEX
    Explanations

    references to Java programming language and its libraries

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

    programming language keywords and namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused79>
    -1.04
    <unused8>
    -1.03
    <unused16>
    -1.03
    <unused28>
    -1.03
    <unused41>
    -1.03
    [@BOS@]
    -1.03
    <unused14>
    -1.03
    <unused23>
    -1.03
    <unused51>
    -1.03
    <unused17>
    -1.03
    POSITIVE LOGITS
    .
    0.43
    ;
    0.34
    ↵↵
    0.33
    <h1>
    0.32
    [
    0.32
    ↵
    0.32
    ),
    0.31
    0
    0.30
    //
    0.29
    ,
    0.29
    Act Density 0.011%

    No Known Activations