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

    Neuronpedia

    INDEX
    Explanations

    places and civic structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    っていない
    -1.05
    Ингредиенты
    -1.02
     contenir
    -1.00
     Bitte
    -0.98
    手表
    -0.98
     hordes
    -0.94
     oar
    -0.93
     nemus
    -0.90
     swar
    -0.89
     forthwith
    -0.89
    POSITIVE LOGITS
    )
    1.15
    ')[
    1.11
    ]
    1.08
    *[
    1.05
    );
    1.04
    }\]
    1.02
    ")[
    1.02
    ;
    1.02
    );\
    1.02
    landse
    1.01
    Act Density 0.073%

    No Known Activations