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

    Neuronpedia

    INDEX
    Explanations

    Expression after token

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ईआरटी
    0.42
    }^{*}$.
    0.42
     Именно
    0.42
    我们在
    0.41
     விடும்
    0.41
     ويكي
    0.41
     આવા
    0.40
     మనం
    0.40
     পারস্পরিক
    0.39
    িষ্ট
    0.39
    POSITIVE LOGITS
    estone
    0.44
    So
    0.40
     After
    0.38
    ходе
    0.38
    After
    0.37
     South
    0.37
    water
    0.37
    South
    0.36
     dopo
    0.36
     efter
    0.36
    Act Density 0.000%

    No Known Activations