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

    Neuronpedia

    INDEX
    Explanations

    sports teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     its
    1.02
    它的
    0.85
     itself
    0.85
     которое
    0.84
    協力
    0.81
    中の
    0.81
    一
    0.79
     Its
    0.79
     Оно
    0.77
     thats
    0.76
    POSITIVE LOGITS
     themselves
    1.27
     kteří
    1.21
     którzy
    1.15
     ktorí
    1.14
     tinham
    1.13
    们
    1.12
     leur
    1.10
     muszą
    1.10
     Their
    1.10
     leurs
    1.09
    Act Density 0.022%

    No Known Activations