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

    Neuronpedia

    INDEX
    Explanations

    closing json brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    》
    -0.98
    -)
    -0.96
    ）
    -0.94
    ↵↵↵↵
    -0.92
    лект
    -0.91
    ↵↵↵↵↵
    -0.91
     '/')
    -0.90
    )
    -0.89
    」
    -0.88
    ↵↵↵↵↵↵
    -0.86
    POSITIVE LOGITS
     "",
    2.61
    ",
    2.48
    »,
    2.47
    (),
    2.44
     [],
    2.33
    ”,
    2.27
    }$,
    2.23
    ],
    2.22
     '',
    2.22
    }",
    2.17
    Act Density 0.022%

    No Known Activations