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

    Neuronpedia

    INDEX
    Explanations

    code block beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ),
    0.38
    })
    0.38
    ])
    0.38
    silhouette
    0.37
    ],
    0.36
    );
    0.36
    },
    0.36
    })=
    0.36
    )},
    0.35
    '_{
    0.35
    POSITIVE LOGITS
     cominci
    0.43
     playwright
    0.40
     masyarakat
    0.38
     comprise
    0.38
     compiler
    0.36
     Сьогодні
    0.36
     தொடங்க
    0.35
    തിനാ
    0.35
    cenik
    0.35
     commencer
    0.35
    Act Density 0.010%

    No Known Activations