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

    Neuronpedia

    INDEX
    Explanations

    population percentages and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     In
    0.44
     in
    0.43
     final
    0.43
    بة
    0.38
     The
    0.38
     end
    0.38
     and
    0.37
     blurring
    0.37
     worldwide
    0.37
     podczas
    0.37
    POSITIVE LOGITS
    Listo
    0.42
     тобто
    0.41
    ्ले
    0.40
     ойно
    0.40
    форд
    0.40
     자체가
    0.40
    amı
    0.39
     банки
    0.39
    也就是
    0.38
     економі
    0.38
    Act Density 0.005%

    No Known Activations