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

    Neuronpedia

    INDEX
    Explanations

    code structure endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vene
    0.88
     किन्तु
    0.87
     व
    0.84
    लेकिन
    0.84
    Namun
    0.83
     बकाया
    0.83
     Гру
    0.82
    但他
    0.81
     अक्सर
    0.81
     Corne
    0.81
    POSITIVE LOGITS
     "))
    0.75
    '))
    0.71
     '))
    0.71
    '));
    0.70
    ."))
    0.70
    ()));
    0.69
    "]))
    0.69
    ]))
    0.69
    ].)
    0.68
    ))=
    0.68
    Act Density 0.112%

    No Known Activations