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

    Neuronpedia

    INDEX
    Explanations

    vehicle steering and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的形式
    0.64
     Sociales
    0.61
    钨
    0.54
    lycer
    0.54
    urada
    0.54
    ungen
    0.51
    cretion
    0.51
    방법
    0.51
    aqueous
    0.50
    throat
    0.50
    POSITIVE LOGITS
     автомобиля
    0.61
    इट
    0.60
    รถ
    0.60
     автомобиль
    0.60
     manoeuv
    0.57
     Citt
    0.57
    行驶
    0.57
     July
    0.55
     voiture
    0.54
    车辆
    0.54
    Act Density 0.036%

    No Known Activations