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

    Neuronpedia

    INDEX
    Explanations

    data structures with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h2>
    -1.38
    ']")
    -1.20
    -1.08
    ]';
    -1.07
    )");
    -1.05
    }`)
    -1.04
    ']
    -1.02
    }`;
    -1.01
    "}
    -1.00
    )";
    -0.97
    POSITIVE LOGITS
    "),
    3.84
    '),
    3.80
    "],
    3.47
    ),
    3.47
    '],
    3.20
    ()),
    3.14
    },
    3.09
    "},
    3.02
    '},
    2.98
     ""),
    2.97
    Act Density 0.191%

    No Known Activations