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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical data and measurements of diversity in various contexts

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

    diversity categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused28>
    -1.04
    <unused23>
    -1.04
    <unused68>
    -1.04
    <unused79>
    -1.04
    <unused16>
    -1.03
    <unused14>
    -1.03
    <unused41>
    -1.03
    <unused43>
    -1.03
    [@BOS@]
    -1.03
    <unused8>
    -1.03
    POSITIVE LOGITS
     for
    0.33
    .
    0.32
    v
    0.30
    )
    0.30
    ↵↵
    0.30
    ↵
    0.28
    可
    0.28
     is
    0.27
     soutenir
    0.27
    </strong>
    0.26
    Act Density 0.087%

    No Known Activations