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

    Neuronpedia

    INDEX
    Explanations

    references to injuries and their circumstances

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

    Text followed by quotation marks

    np_acts-logits-general · gemini-2.0-flash

    text within quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </caption>
    -1.02
    </td>
    -0.96
    </h1>
    -0.89
    }}/>
    -0.88
    </th>
    -0.86
    </code>
    -0.85
    </sub>
    -0.83
     şi
    -0.81
    ↵↵↵↵↵
    -0.79
    )",
    -0.79
    POSITIVE LOGITS
    ,”
    1.81
    ,’
    1.67
    ,"
    1.55
    ,’”
    1.42
    ,»
    1.41
    ,’’
    1.36
    ,'
    1.32
    ),”
    1.32
    ,''
    1.32
    ,'"
    1.28
    Act Density 0.387%

    No Known Activations