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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis or quote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </blockquote>
    1.83
    <blockquote>
    1.50
    }`;
    0.91
    </em>
    0.91
     继续访问
    0.75
    .’
    0.75
    ।’
    0.72
    =?";
    0.71
     />';
    0.70
    ’.”
    0.68
    POSITIVE LOGITS
    ")
    4.33
    ").
    4.05
     ")
    3.85
    "),
    3.82
    "):
    3.78
    .")
    3.75
    ?")
    3.59
    !")
    3.47
    ')
    3.47
     ").
    3.45
    Act Density 0.492%

    No Known Activations