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

    Neuronpedia

    INDEX
    Explanations

    the start of a document

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

    HTML table-related tokens

    np_acts-logits-general · gemini-2.0-flash

    differences, subjected, against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enggak
    -0.57
    Eksteraj
    -0.52
     "
    -0.51
     
    -0.51
    __.__
    -0.51
    آباد
    -0.49
     
    -0.47
    iltà
    -0.44
    %")
    -0.43
     uParam
    -0.43
    POSITIVE LOGITS
    </td>
    2.18
    </th>
    1.61
    </code>
    1.49
    </h1>
    1.30
    </h4>
    1.29
    </blockquote>
    1.26
    </caption>
    1.22
    </h3>
    1.13
    </h6>
    1.06
    "/>
    1.05
    Act Density 0.038%

    No Known Activations