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

    Neuronpedia

    INDEX
    Explanations

    elements related to cause and effect in scientific contexts

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

    Text following specific punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    such additive inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </i>
    -1.17
    </b>
    -0.78
    --
    -0.70
    &#
    -0.67
    </th>
    -0.66
    ⁩
    -0.64
     --
    -0.61
    <i>
    -0.61
     &#
    -0.61
    </code>
    -0.60
    POSITIVE LOGITS
    AddTagHelper
    1.01
    </strong>
    0.99
    adaptiveStyles
    0.97
    )";
    0.92
     kohdetta
    0.86
     …
    0.85
    MigrationBuilder
    0.81
    )…
    0.81
     chi̍t
    0.81
     """
    0.79
    Act Density 0.273%

    No Known Activations