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

    Neuronpedia

    INDEX
    Explanations

    closing brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <start_of_image>
    1.76
    ')));
    0.76
    <h2>
    0.72
    ')))
    0.70
    </h2>
    0.67
     \"
    0.67
    。《
    0.66
    '));
    0.64
     "));
    0.63
    \"{
    0.63
    POSITIVE LOGITS
    ]
    5.07
    ],
    4.59
    ].
    4.33
    ](
    4.32
    ]:
    4.30
     ]
    4.29
    .]
    4.28
    ];
    4.27
    ']
    4.15
    !]
    4.05
    Act Density 0.888%

    No Known Activations