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

    Neuronpedia

    INDEX
    Explanations

    movement decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Được
    0.87
     zdravot
    0.86
     Đây
    0.85
     آبادی
    0.85
     केजरीवाल
    0.83
    ಿಯು
    0.82
     chiều
    0.81
     এলাক
    0.81
     دوربین
    0.79
     huyện
    0.78
    POSITIVE LOGITS
    ,
    0.91
     ferm
    0.73
    шей
    0.71
    dise
    0.71
    dings
    0.66
    Dise
    0.66
    MNOP
    0.65
    I
    0.65
    plain
    0.64
    ploy
    0.64
    Act Density 0.001%

    No Known Activations