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

    Neuronpedia

    INDEX
    Explanations

    monetary values and numerical expressions related to pricing or financial information

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

    special characters followed by ampersand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.91
    expandindo
    -0.88
    mpagne
    -0.86
    IsContent
    -0.85
    <unused79>
    -0.84
    <unused8>
    -0.84
    <unused28>
    -0.84
    <unused3>
    -0.84
    <pad>
    -0.84
    [@BOS@]
    -0.84
    POSITIVE LOGITS
    ,
    0.56
    </em>
    0.54
    </i>
    0.51
    </td>
    0.49
    )
    0.49
    .
    0.46
    </b>
    0.45
    </strong>
    0.45
    </sup>
    0.41
    ↵
    0.40
    Act Density 0.067%

    No Known Activations