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

    Neuronpedia

    INDEX
    Explanations

    titles or headings highlighting schedules and updates for breaks

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

    HTML tags and formatting

    np_acts-logits-general · gemini-2.0-flash

    HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fi
    -1.72
     fl
    -1.61
    </em>
    -1.60
    </strong>
    -1.59
     first
    -1.57
    fl
    -1.47
     
    -1.45
    fi
    -1.40
    ."""
    -1.18
     """
    -1.12
    POSITIVE LOGITS
    </b>
    3.92
    </i>
    3.51
    <b>
    3.20
    <i>
    2.94
    dfrac
    1.78
    例文帳に追加
    1.51
    </td>
    1.49
    <u>
    1.30
    <sup>
    1.19
     + 
    1.16
    Act Density 0.813%

    No Known Activations