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

    Neuronpedia

    INDEX
    Explanations

    end of parenthetical phrases or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "";
    0.39
    IDField
    0.39
    ！（
    0.38
     etcétera
    0.37
    ="";
    0.33
    ன்களை
    0.33
     ("",
    0.33
     habitudes
    0.33
    द्रता
    0.33
    :"",
    0.33
    POSITIVE LOGITS
    )
    1.09
    ):
    1.01
    ),
    0.99
    )-
    0.95
    ）
    0.94
    )،
    0.91
    )/
    0.88
    ?)
    0.85
    ))
    0.83
     )
    0.83
    Act Density 0.125%

    No Known Activations