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

    Neuronpedia

    INDEX
    Explanations

    code delimiters or arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h2>
    0.90
    、
    0.88
    ]}$.
    0.83
    ”
    0.83
    </h1>
    0.82
    。）
    0.79
    ।]
    0.77
     ہو۔
    0.76
    .’”
    0.75
    ]}$
    0.75
    POSITIVE LOGITS
    ",
    3.76
    ),
    3.65
    “,
    3.65
    `,
    3.46
     ",
    3.44
    ],
    3.41
    ”,
    3.40
    »,
    3.37
    },
    3.30
    >,
    3.26
    Act Density 1.718%

    No Known Activations