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

    Neuronpedia

    INDEX
    Explanations

    HTML tags, specifically those related to strong emphasis or bold formatting

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

    scheduling and break options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.68
    +#+#
    -0.60
     chrétien
    -0.59
    verifyException
    -0.58
     Chwiliwch
    -0.57
     تضيفلها
    -0.57
    RenderAtEndOf
    -0.56
    StoryboardSegue
    -0.56
     Signalez
    -0.55
    styleType
    -0.55
    POSITIVE LOGITS
    </strong>
    1.02
    </em>
    0.80
    </b>
    0.78
    </u>
    0.69
    </i>
    0.62
    </sub>
    0.60
    </s>
    0.59
    ]')
    0.56
    </sup>
    0.54
    }]
    0.54
    Act Density 0.011%

    No Known Activations